New version 3.0.3

.codecov.yml

@@ -1,12 +0,0 @@
-codecov:
-  notify:
-    require_ci_to_pass: yes
-
-coverage:
-  status:
-    project:
-      default:
-        threshold: 1%
-
-ignore:
-  - "test"

.github/FUNDING.yml

@@ -1,12 +0,0 @@
-# These are supported funding model platforms
-
-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
-patreon: # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-custom: https://kiwix.org/support-us/

.github/move.yml

@@ -1,27 +0,0 @@
-# Configuration for Move Issues - https://github.com/dessant/move-issues
-
-# Delete the command comment when it contains no other content
-deleteCommand: true
-
-# Close the source issue after moving
-closeSourceIssue: true
-
-# Lock the source issue after moving
-lockSourceIssue: false
-
-# Mention issue and comment authors
-mentionAuthors: true
-
-# Preserve mentions in the issue content
-keepContentMentions: true
-
-# Move labels that also exist on the target repository
-moveLabels: true
-
-# Set custom aliases for targets
-# aliases:
-#   r: repo
-#   or: owner/repo
-
-# Repository to extend settings from
-# _extends: repo

.github/stale.yml

@@ -1,15 +0,0 @@
-daysUntilClose: false
-staleLabel: stale
-
-issues:
-  daysUntilStale: 60
-  markComment: >
-    This issue has been automatically marked as stale because it has not had
-    recent activity. It will be now be reviewed manually. Thank you
-    for your contributions.
-pulls:
-   daysUntilStale: 7
-   markComment: >
-     This pull request has been automatically marked as stale because it has not had
-     recent activity. It will be now be reviewed manually. Thank you
-     for your contributions.

.gitignore

@@ -1,3 +0,0 @@
-.idea/
-*.swp
-subprojects/googletest-release*

.travis.yml

@@ -1,6 +1,6 @@
 language: cpp
-dist: xenial
-sudo: true
+dist: trusty
+sudo: false
 cache: ccache
 before_install:
 - PATH=$PATH:$HOME/bin
@@ -18,7 +18,6 @@ addons:
   apt:
     packages:
       - cmake
-      - python3.5
       - python3-pip
       - libbz2-dev
       - ccache
@@ -31,11 +30,6 @@ addons:
       - gcc-mingw-w64-i686
       - gcc-mingw-w64-base
       - mingw-w64-tools
-      - gcovr
-  homebrew:
-    update: true
-    packages:
-      - gcovr
 matrix:
   include:
     - env: PLATFORM="native_dyn"

COPYING

@@ -77,7 +77,7 @@ modification follow.
 
   "Copyright" also means copyright-like laws that apply to other kinds of
 works, such as semiconductor masks.
-
+ 
   "The Program" refers to any copyrightable work licensed under this
 License.  Each licensee is addressed as "you".  "Licensees" and
 "recipients" may be individuals or organizations.
@@ -510,7 +510,7 @@ actual knowledge that, but for the patent license, your conveying the
 covered work in a country, or your recipient's use of the covered work
 in a country, would infringe one or more identifiable patents in that
 country that you have reason to believe are valid.
-
+  
   If, pursuant to or in connection with a single transaction or
 arrangement, you convey, or propagate by procuring conveyance of, a
 covered work, and grant a patent license to some of the parties

ChangeLog

@@ -1,150 +1,3 @@
-kiwix-lib 8.2.2
-===============
-
- * Improve a few compilation scripts
-
-kiwix-lib 8.2.1
-===============
-
- * Reintroduce kiwix-serve taskbar
-
-kiwix-lib 8.2.0
-===============
-
- * More debug information if aria2c command fails
- * Allow to set kiwix-serve port
- * Better (dead) bookmarks mgmt
-
-kiwix-lib 8.1.0
-===============
-
- * Fix pathTools manipulation.
- * Add missing implementation of getArticleCount and getMediaCount on android.
- * Correctly convert windows path to utf8.
- * Add code coverage in the CI
-
-kiwix-lib 8.0.1
-===============
-
- * Fix join function
-
-kiwix-lib 8.0.0
-===============
-
- * Add new methods to get all (and new) metadata from the zim file.
- * Add methods to get the value of a specific tag.
- * [API Change] Convert tags value to the new convention.
- * [API Change] Rename `getMatatag` method to `getMetadata`
- * [ABI Change] Correctly detect executable path in appimage.
-
-kiwix-lib 7.0.0
-===============
-
- * [API break] Add a argument to kiwix-serve to specify the library to use.
-
-kiwix-lib 6.0.4
-===============
-
- * Fix HTML rendering of the search result if there is no result.
- * Do not crash at html rendering if request ask for 0 results (start == end)
- * Correctly find the executable path if we are using AppImage
-
-kiwix-lib 6.0.3
-===============
-
- * force one column suggestion in kiwix-serve suggestions
- * fix fulltext search link in suggestions
- * UI fixes in kiwix-serve rendering
-
-kiwix-lib 6.0.2
-===============
-
- * Correctly set the groupId in the pom file.
-
-kiwix-lib 6.0.1
-===============
-
- * Generate the pom file for android/maven
-
-kiwix-lib 6.0.0
-===============
-
- * Move the server code in kiwix-lib (from kiwix-serve).
- * Add unit test on regex functions.
- * Fix computerAbsolutePath (thread safe, memory leak).
- * Correctly set the book's path as valid if we construct the book from a
-   reader.
- * [JNI] Add a method to know if a article is a redirection.
- * Do not embed the gtest dependency.
- * [JNI] Add a constructor to JNIKiwixString.
- * Change order of search of the favicon urls.
- * Clean a lot of unecessary includes in headers. (potential "API break")
-
-kiwix-lib 5.2.0
-===============
-
- * kiwix-serve integration (as a seperated process).
- * Fix crash in the suggestion search.
- * Better API to filter the library books.
- * New kiwix-lib application for android. (.aar)
- * Use ReLinker to link with libkiwix.so in android.
- * Correctly set the verbosity of zim search.
-
-kiwix-lib 5.1.0
-===============
-
- * Add function to pause, resume and stop downloads.
- * Add zim's tags in the opds stream.
- * Addapt to new libzim 5.0.0 API.
-
-kiwix-lib 5.0.0
-===============
-
- * Remove error message when trying to open an wrong zim file.
- * Rewrite `makeTmpDirectory` to not use uuid functions on windows.
- * [API break] Remove `getNetworkInterfaces` and `getBestPublicIp`.
- * Remove rpath
- * Detect infinite (and too long) redirect loops.
-
-kiwix-lib 4.1.0
-===============
-
- * Allow the library to be filtered by tags.
- * Fix language mapping.
- * Update README about mustache dependency.
-
-kiwix-lib 4.0.1
-===============
-
- * Fix "maybe uninitialize variable" issue.
- * Ensure path are stored correctly (absolute path) in the library.
- * [CI] Use the new deps archive xz
-
-kiwix-lib 4.0.0
-===============
-
- * [API break] Remove support for external index.
- * Move to the mustache templating system instead of ctpp2.
- * Make meson.build works for meson>=0.43.0
- * [API break] Move the basic tools from the `common` directory to `tools`.
-
-kiwix-lib 3.1.1
-===============
-
- * The OPDS feed book's date must be the date of the book, not the date of the
- feed generation.
- * Convert the standard opds date to our format (YYYY-MM-DD)
- * Remove duplicate language attribute in the libxml dumper.
- * Create the datadirectory to not fail to write a file in a non-existent
-   directory
-
-kiwix-lib 3.1.0
-===============
-
- * Add a method to get the favicon url of book (if available).
- * Move dump code of library.xml in a specific class.
- * Add a first support to bookmarks
-
 kiwix-lib 3.0.3
 ===============
 
@@ -152,7 +5,6 @@ kiwix-lib 3.0.3
  ('eng').
  * Correctly write the 'ArticleCount' and 'MediaCount' in the library.xml.
  * Correctly fill the book size for the zim file size.
- * Fix launch of aria2c.
 
 kiwix-lib 3.0.2
 ===============

README.md

@@ -1,16 +1,8 @@
 Kiwix library
 =============
 
-The Kiwix library provides the [Kiwix](https://kiwix.org) software
-suite core. It contains the code shared by all Kiwix ports (Windows,
-GNU/Linux, macOS, Android, iOS, ...).
-
-[![Download](https://api.bintray.com/packages/kiwix/kiwix/kiwixlib/images/download.svg)](https://bintray.com/kiwix/kiwix/kiwixlib/_latestVersion)
-[![AUR version](https://img.shields.io/aur/version/kiwix-lib)](https://aur.archlinux.org/packages/kiwix-lib/)
-[![Build Status](https://travis-ci.com/kiwix/kiwix-lib.svg?branch=master)](https://travis-ci.com/kiwix/kiwix-lib)
-[![CodeFactor](https://www.codefactor.io/repository/github/kiwix/kiwix-lib/badge)](https://www.codefactor.io/repository/github/kiwix/kiwix-lib)
-[![Codecov](https://codecov.io/gh/kiwix/kiwix-lib/branch/master/graph/badge.svg)](https://codecov.io/gh/kiwix/kiwix-lib)
-[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
+The Kiwix library provides the Kiwix software core. It contains the
+code shared by all Kiwix ports (Windows, Linux, OSX, Android, ...).
 
 Disclaimer
 ----------
@@ -35,13 +27,18 @@ The Kiwix library relies on many third parts software libraries. They
 are prerequisites to the Kiwix library compilation. Following
 libraries need to be available:
 
-* [ICU](https://site.icu-project.org/) (package `libicu-dev` on Ubuntu)
-* [ZIM](https://openzim.org/) (package `libzim-dev` on Ubuntu)
-* [Pugixml](https://pugixml.org/) (package `libpugixml-dev` on Ubuntu)
-* [Aria2](https://aria2.github.io/) (package `aria2` on Ubuntu)
-* [Mustache](https://github.com/kainjow/Mustache) (Just copy the
-header `mustache.hpp` somewhere it can be found by the compiler and/or
-set CPPFLAGS with correct `-I` option)
+* ICU ................................... http://site.icu-project.org/
+(package libicu-dev on Ubuntu)
+* ZIM ........................................ http://www.openzim.org/
+(package libzim-dev on Ubuntu)
+* Pugixml ........................................ http://pugixml.org/
+(package libpugixml-dev on Ubuntu)
+* ctpp2 ........................................ http://ctpp.havoc.ru/
+(package libctpp2-dev on Ubuntu)
+* Xapian ......................................... https://xapian.org/
+(package libxapian-dev on Ubuntu)
+* libaria2 .................................. https://aria2.github.io/
+(no package on Ubuntu)
 
 These dependencies may or may not be packaged by your operating
 system. They may also be packaged but only in an older version. The
@@ -50,30 +47,33 @@ In the worse case, you will have to download and compile bleeding edge
 version by hand.
 
 If you want to install these dependencies locally, then use the
-`kiwix-lib` directory as install prefix.
+kiwix-lib directory as install prefix.
+
+If you compile ctpp2 from source and want to compile the Kiwix library
+statically then you will probably need to rename ctpp2 static library
+from ctpp2-st.a to ctpp2.a.
 
 Environment
 -------------
 
-The Kiwix library builds using [Meson](https://mesonbuild.com/) version
-0.43 or higher. Meson relies itself on Ninja, pkg-config and few other
+The Kiwix library builds using [Meson](http://mesonbuild.com/) version
+0.39 or higher. Meson relies itself on Ninja, pkg-config and few other
 compilation tools.
 
 Install first the few common compilation tools:
-* [Meson](https://mesonbuild.com/)
-* [Ninja](https://ninja-build.org/)
-* [pkg-config](https://www.freedesktop.org/wiki/Software/pkg-config/)
+* Meson
+* Ninja
+* Pkg-config
 
 These tools should be packaged if you use a cutting edge operating
-system. If not, have a look to the [Troubleshooting](#Troubleshooting)
-section.
+system. If not, have a look to the "Troubleshooting" section.
 
 Compilation
 -----------
 
 Once all dependencies are installed, you can compile the Kiwix library
 with:
-```bash
+```
 meson . build
 ninja -C build
 ```
@@ -90,30 +90,32 @@ Installation
 
 If you want to install the Kiwix library and the headers you just have
 compiled on your system, here we go:
-```bash
+
+```
 ninja -C build install
 ```
 
-You might need to run the command as root (or using `sudo`), depending
+You might need to run the command as root (or using 'sudo'), depending
 where you want to install the libraries. After the installation
-succeeded, you may need to run `ldconfig` (as `root`).
+succeeded, you may need to run ldconfig (as root).
 
 Uninstallation
 ------------
 
 If you want to uninstall the Kiwix library:
-```bash
+
+```
 ninja -C build uninstall
 ```
 
-Like for the installation, you might need to run the command as `root`
-(or using `sudo`).
+Like for the installation, you might need to run the command as root
+(or using 'sudo').
 
 Troubleshooting
 ---------------
 
 If you need to install Meson "manually":
-```bash
+```
 virtualenv -p python3 ./ # Create virtualenv
 source bin/activate      # Activate the virtualenv
 pip3 install meson       # Install Meson
@@ -121,7 +123,7 @@ hash -r                  # Refresh bash paths
 ```
 
 If you need to install Ninja "manually":
-```bash
+```
 git clone git://github.com/ninja-build/ninja.git
 cd ninja
 git checkout release
@@ -140,5 +142,4 @@ repository.
 License
 -------
 
-[GPLv3](https://www.gnu.org/licenses/gpl-3.0) or later, see
-[COPYING](COPYING) for more details.
+GPLv3 or later, see COPYING for more details.

android-kiwix-lib-publisher/.gitignore

@@ -1,13 +0,0 @@
-*.iml
-.gradle
-/local.properties
-/.idea/caches
-/.idea/libraries
-/.idea/modules.xml
-/.idea/workspace.xml
-/.idea/navEditor.xml
-/.idea/assetWizardSettings.xml
-.DS_Store
-/build
-/captures
-.externalNativeBuild

android-kiwix-lib-publisher/build.gradle

@@ -1,25 +0,0 @@
-// Top-level build file where you can add configuration options common to all sub-projects/modules.
-
-buildscript {
-    repositories {
-        google()
-        jcenter()
-
-    }
-    dependencies {
-        classpath 'com.android.tools.build:gradle:3.4.1'
-        // NOTE: Do not place your application dependencies here; they belong
-        // in the individual module build.gradle files
-    }
-}
-
-allprojects {
-    repositories {
-        google()
-        jcenter()
-    }
-}
-
-task clean(type: Delete) {
-    delete rootProject.buildDir
-}

android-kiwix-lib-publisher/gradle.properties

@@ -1,15 +0,0 @@
-# Project-wide Gradle settings.
-# IDE (e.g. Android Studio) users:
-# Gradle settings configured through the IDE *will override*
-# any settings specified in this file.
-# For more details on how to configure your build environment visit
-# http://www.gradle.org/docs/current/userguide/build_environment.html
-# Specifies the JVM arguments used for the daemon process.
-# The setting is particularly useful for tweaking memory settings.
-org.gradle.jvmargs=-Xmx1536m
-# When configured, Gradle will run in incubating parallel mode.
-# This option should only be used with decoupled projects. More details, visit
-# http://www.gradle.org/docs/current/userguide/multi_project_builds.html#sec:decoupled_projects
-# org.gradle.parallel=true
-# Kotlin code style for this project: "official" or "obsolete":
-kotlin.code.style=official

android-kiwix-lib-publisher/gradle/wrapper/gradle-wrapper.properties

@@ -1,6 +0,0 @@
-#Wed Jun 19 15:28:39 BST 2019
-distributionBase=GRADLE_USER_HOME
-distributionPath=wrapper/dists
-zipStoreBase=GRADLE_USER_HOME
-zipStorePath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-5.1.1-all.zip

android-kiwix-lib-publisher/gradlew

@@ -1,172 +0,0 @@
-#!/usr/bin/env sh
-
-##############################################################################
-##
-##  Gradle start up script for UN*X
-##
-##############################################################################
-
-# Attempt to set APP_HOME
-# Resolve links: $0 may be a link
-PRG="$0"
-# Need this for relative symlinks.
-while [ -h "$PRG" ] ; do
-    ls=`ls -ld "$PRG"`
-    link=`expr "$ls" : '.*-> \(.*\)$'`
-    if expr "$link" : '/.*' > /dev/null; then
-        PRG="$link"
-    else
-        PRG=`dirname "$PRG"`"/$link"
-    fi
-done
-SAVED="`pwd`"
-cd "`dirname \"$PRG\"`/" >/dev/null
-APP_HOME="`pwd -P`"
-cd "$SAVED" >/dev/null
-
-APP_NAME="Gradle"
-APP_BASE_NAME=`basename "$0"`
-
-# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
-DEFAULT_JVM_OPTS=""
-
-# Use the maximum available, or set MAX_FD != -1 to use that value.
-MAX_FD="maximum"
-
-warn () {
-    echo "$*"
-}
-
-die () {
-    echo
-    echo "$*"
-    echo
-    exit 1
-}
-
-# OS specific support (must be 'true' or 'false').
-cygwin=false
-msys=false
-darwin=false
-nonstop=false
-case "`uname`" in
-  CYGWIN* )
-    cygwin=true
-    ;;
-  Darwin* )
-    darwin=true
-    ;;
-  MINGW* )
-    msys=true
-    ;;
-  NONSTOP* )
-    nonstop=true
-    ;;
-esac
-
-CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
-
-# Determine the Java command to use to start the JVM.
-if [ -n "$JAVA_HOME" ] ; then
-    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
-        # IBM's JDK on AIX uses strange locations for the executables
-        JAVACMD="$JAVA_HOME/jre/sh/java"
-    else
-        JAVACMD="$JAVA_HOME/bin/java"
-    fi
-    if [ ! -x "$JAVACMD" ] ; then
-        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
-
-Please set the JAVA_HOME variable in your environment to match the
-location of your Java installation."
-    fi
-else
-    JAVACMD="java"
-    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
-
-Please set the JAVA_HOME variable in your environment to match the
-location of your Java installation."
-fi
-
-# Increase the maximum file descriptors if we can.
-if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
-    MAX_FD_LIMIT=`ulimit -H -n`
-    if [ $? -eq 0 ] ; then
-        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
-            MAX_FD="$MAX_FD_LIMIT"
-        fi
-        ulimit -n $MAX_FD
-        if [ $? -ne 0 ] ; then
-            warn "Could not set maximum file descriptor limit: $MAX_FD"
-        fi
-    else
-        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
-    fi
-fi
-
-# For Darwin, add options to specify how the application appears in the dock
-if $darwin; then
-    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
-fi
-
-# For Cygwin, switch paths to Windows format before running java
-if $cygwin ; then
-    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
-    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
-    JAVACMD=`cygpath --unix "$JAVACMD"`
-
-    # We build the pattern for arguments to be converted via cygpath
-    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
-    SEP=""
-    for dir in $ROOTDIRSRAW ; do
-        ROOTDIRS="$ROOTDIRS$SEP$dir"
-        SEP="|"
-    done
-    OURCYGPATTERN="(^($ROOTDIRS))"
-    # Add a user-defined pattern to the cygpath arguments
-    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
-        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
-    fi
-    # Now convert the arguments - kludge to limit ourselves to /bin/sh
-    i=0
-    for arg in "$@" ; do
-        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
-        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
-
-        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
-            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
-        else
-            eval `echo args$i`="\"$arg\""
-        fi
-        i=$((i+1))
-    done
-    case $i in
-        (0) set -- ;;
-        (1) set -- "$args0" ;;
-        (2) set -- "$args0" "$args1" ;;
-        (3) set -- "$args0" "$args1" "$args2" ;;
-        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
-        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
-        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
-        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
-        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
-        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
-    esac
-fi
-
-# Escape application args
-save () {
-    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
-    echo " "
-}
-APP_ARGS=$(save "$@")
-
-# Collect all arguments for the java command, following the shell quoting and substitution rules
-eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
-
-# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
-if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
-  cd "$(dirname "$0")"
-fi
-
-exec "$JAVACMD" "$@"

android-kiwix-lib-publisher/gradlew.bat

@@ -1,84 +0,0 @@
-@if "%DEBUG%" == "" @echo off
-@rem ##########################################################################
-@rem
-@rem  Gradle startup script for Windows
-@rem
-@rem ##########################################################################
-
-@rem Set local scope for the variables with windows NT shell
-if "%OS%"=="Windows_NT" setlocal
-
-set DIRNAME=%~dp0
-if "%DIRNAME%" == "" set DIRNAME=.
-set APP_BASE_NAME=%~n0
-set APP_HOME=%DIRNAME%
-
-@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
-set DEFAULT_JVM_OPTS=
-
-@rem Find java.exe
-if defined JAVA_HOME goto findJavaFromJavaHome
-
-set JAVA_EXE=java.exe
-%JAVA_EXE% -version >NUL 2>&1
-if "%ERRORLEVEL%" == "0" goto init
-
-echo.
-echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
-echo.
-echo Please set the JAVA_HOME variable in your environment to match the
-echo location of your Java installation.
-
-goto fail
-
-:findJavaFromJavaHome
-set JAVA_HOME=%JAVA_HOME:"=%
-set JAVA_EXE=%JAVA_HOME%/bin/java.exe
-
-if exist "%JAVA_EXE%" goto init
-
-echo.
-echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
-echo.
-echo Please set the JAVA_HOME variable in your environment to match the
-echo location of your Java installation.
-
-goto fail
-
-:init
-@rem Get command-line arguments, handling Windows variants
-
-if not "%OS%" == "Windows_NT" goto win9xME_args
-
-:win9xME_args
-@rem Slurp the command line arguments.
-set CMD_LINE_ARGS=
-set _SKIP=2
-
-:win9xME_args_slurp
-if "x%~1" == "x" goto execute
-
-set CMD_LINE_ARGS=%*
-
-:execute
-@rem Setup the command line
-
-set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
-
-@rem Execute Gradle
-"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
-
-:end
-@rem End local scope for the variables with windows NT shell
-if "%ERRORLEVEL%"=="0" goto mainEnd
-
-:fail
-rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
-rem the _cmd.exe /c_ return code!
-if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
-exit /b 1
-
-:mainEnd
-if "%OS%"=="Windows_NT" endlocal
-
-:omega

android-kiwix-lib-publisher/kiwixLibAndroid/.gitignore

@@ -1 +0,0 @@
-/build

android-kiwix-lib-publisher/kiwixLibAndroid/build.gradle

@@ -1,64 +0,0 @@
-apply plugin: 'com.android.library'
-apply plugin: 'maven'
-
-android {
-    compileSdkVersion 28
-    defaultConfig {
-        minSdkVersion 15
-        targetSdkVersion 28
-        versionCode 1
-        versionName "1.0"
-    }
-    buildTypes {
-        release {
-            minifyEnabled false
-            proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
-        }
-    }
-}
-
-dependencies {
-    implementation 'com.getkeepsafe.relinker:relinker:1.3.1'
-}
-
-task writePom {
-  pom {
-    project {
-        groupId 'org.kiwix.kiwixlib'
-        artifactId 'kiwixlib'
-        version '8.2.2' + (System.env.KIWIXLIB_BUILDVERSION == null ? '' : '-'+System.env.KIWIXLIB_BUILDVERSION)
-        packaging 'aar'
-        name 'kiwixlib'
-        url 'https://github.com/kiwix/kiwix-lib'
-        licenses {
-            license {
-                name 'GPLv3'
-                url 'https://www.gnu.org/licenses/gpl-3.0.en.html'
-            }
-        }
-      developers {
-          developer {
-              id 'kiwix'
-              name 'kiwix'
-              email 'contact@kiwix.org'
-          }
-      }
-      scm {
-          connection 'https://github.com/kiwix/kiwix-lib.git'
-          developerConnection 'https://github.com/kiwix/kiwix-lib.git'
-          url 'https://github.com/kiwix/kiwix-lib'
-      }
-    }
-  }.withXml {
-    def dependenciesNode = asNode().appendNode('dependencies')
-
-    //Iterate over the implementation dependencies, adding a <dependency> node for each
-    configurations.implementation.allDependencies.each {
-      def dependencyNode = dependenciesNode.appendNode('dependency')
-      dependencyNode.appendNode('groupId', it.group)
-      dependencyNode.appendNode('artifactId', it.name)
-      dependencyNode.appendNode('version', it.version)
-    }
-  }.writeTo("$buildDir/pom.xml")
-}
-

android-kiwix-lib-publisher/kiwixLibAndroid/proguard-rules.pro

@@ -1,21 +0,0 @@
-# Add project specific ProGuard rules here.
-# You can control the set of applied configuration files using the
-# proguardFiles setting in build.gradle.
-#
-# For more details, see
-#   http://developer.android.com/guide/developing/tools/proguard.html
-
-# If your project uses WebView with JS, uncomment the following
-# and specify the fully qualified class name to the JavaScript interface
-# class:
-#-keepclassmembers class fqcn.of.javascript.interface.for.webview {
-#   public *;
-#}
-
-# Uncomment this to preserve the line number information for
-# debugging stack traces.
-#-keepattributes SourceFile,LineNumberTable
-
-# If you keep the line number information, uncomment this to
-# hide the original source file name.
-#-renamesourcefileattribute SourceFile

android-kiwix-lib-publisher/kiwixLibAndroid/src/main/AndroidManifest.xml

@@ -1,10 +0,0 @@
-<manifest xmlns:android="http://schemas.android.com/apk/res/android"
-    package="kiwix.org.kiwixlib">
-
-    <application
-        android:allowBackup="true"
-        android:supportsRtl="true">
-
-    </application>
-
-</manifest>

android-kiwix-lib-publisher/settings.gradle

@@ -1 +0,0 @@
-include ':kiwixLibAndroid'

include/book.h

@@ -28,6 +28,7 @@ class xml_node;
 
 namespace kiwix
 {
+enum supportedIndexType { UNKNOWN, XAPIAN };
 
 class OPDSDumper;
 class Reader;
@@ -45,12 +46,14 @@ class Book
   void update(const Reader& reader);
   void updateFromXml(const pugi::xml_node& node, const std::string& baseDir);
   void updateFromOpds(const pugi::xml_node& node, const std::string& urlHost);
-  std::string getHumanReadableIdFromPath() const;
+  std::string getHumanReadableIdFromPath();
 
   bool readOnly() const { return m_readOnly; }
   const std::string& getId() const { return m_id; }
   const std::string& getPath() const { return m_path; }
   bool isPathValid() const { return m_pathValid; }
+  const std::string& getIndexPath() const { return m_indexPath; }
+  const supportedIndexType& getIndexType() const { return m_indexType; }
   const std::string& getTitle() const { return m_title; }
   const std::string& getDescription() const { return m_description; }
   const std::string& getLanguage() const { return m_language; }
@@ -65,7 +68,6 @@ class Book
   const uint64_t& getMediaCount() const { return m_mediaCount; }
   const uint64_t& getSize() const { return m_size; }
   const std::string& getFavicon() const;
-  const std::string& getFaviconUrl() const { return m_faviconUrl; }
   const std::string& getFaviconMimeType() const { return m_faviconMimeType; }
   const std::string& getDownloadId() const { return m_downloadId; }
 
@@ -73,6 +75,8 @@ class Book
   void setId(const std::string& id) { m_id = id; }
   void setPath(const std::string& path);
   void setPathValid(bool valid) { m_pathValid = valid; }
+  void setIndexPath(const std::string& indexPath);
+  void setIndexType(supportedIndexType indexType) { m_indexType = indexType;}
   void setTitle(const std::string& title) { m_title = title; }
   void setDescription(const std::string& description) { m_description = description; }
   void setLanguage(const std::string& language) { m_language = language; }
@@ -95,6 +99,8 @@ class Book
   std::string m_downloadId;
   std::string m_path;
   bool m_pathValid;
+  std::string m_indexPath;
+  supportedIndexType m_indexType;
   std::string m_title;
   std::string m_description;
   std::string m_language;

include/bookmark.h

@@ -1,68 +0,0 @@
-/*
- * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_BOOKMARK_H
-#define KIWIX_BOOKMARK_H
-
-#include <string>
-
-namespace pugi {
-class xml_node;
-}
-
-namespace kiwix
-{
-
-/**
- * A class to store information about a bookmark (an article in a book)
- */
-class Bookmark
-{
- public:
-  Bookmark();
-  ~Bookmark();
-
-  void updateFromXml(const pugi::xml_node& node);
-
-  const std::string& getBookId() const { return m_bookId; }
-  const std::string& getBookTitle()  const { return m_bookTitle; }
-  const std::string& getUrl() const { return m_url; }
-  const std::string& getTitle() const { return m_title; }
-  const std::string& getLanguage() const { return m_language; }
-  const std::string& getDate() const { return m_date; }
-
-  void setBookId(const std::string& bookId) { m_bookId = bookId; }
-  void setBookTitle(const std::string& bookTitle) { m_bookTitle = bookTitle; }
-  void setUrl(const std::string& url) { m_url = url; }
-  void setTitle(const std::string& title) { m_title = title; }
-  void setLanguage(const std::string& language) { m_language = language; }
-  void setDate(const std::string& date) { m_date = date; }
-
- protected:
-  std::string m_bookId;
-  std::string m_bookTitle;
-  std::string m_url;
-  std::string m_title;
-  std::string m_language;
-  std::string m_date;
-};
-
-}
-
-#endif

include/common/networkTools.h

@@ -20,10 +20,13 @@
 #ifndef KIWIX_NETWORKTOOLS_H
 #define KIWIX_NETWORKTOOLS_H
 
+#include <map>
 #include <string>
 
 namespace kiwix
 {
+std::map<std::string, std::string> getNetworkInterfaces();
+std::string getBestPublicIp();
 std::string download(const std::string& url);
 }
 

include/common/otherTools.h

@@ -20,16 +20,18 @@
 #ifndef KIWIX_OTHERTOOLS_H
 #define KIWIX_OTHERTOOLS_H
 
-#include <string>
+#ifdef _WIN32
+#include <windows.h>
+#else
+#include <unistd.h>
+#endif
 
-namespace pugi {
-  class xml_node;
-}
+#include <pugixml.hpp>
 
 namespace kiwix
 {
 void sleep(unsigned int milliseconds);
-std::string nodeToString(const pugi::xml_node& node);
+std::string nodeToString(pugi::xml_node node);
 std::string converta2toa3(const std::string& a2code);
 }
 

include/common/pathTools.h

@@ -0,0 +1,64 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_PATHTOOLS_H
+#define KIWIX_PATHTOOLS_H
+
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <fstream>
+#include <ios>
+#include <iostream>
+#include <sstream>
+#include <string>
+#include <vector>
+
+#ifdef _WIN32
+#include <direct.h>
+#endif
+
+#include "stringTools.h"
+
+using namespace std;
+
+bool isRelativePath(const string& path);
+string computeAbsolutePath(const string path, const string relativePath);
+string computeRelativePath(const string path, const string absolutePath);
+string removeLastPathElement(const string path,
+                             const bool removePreSeparator = false,
+                             const bool removePostSeparator = false);
+string appendToDirectory(const string& directoryPath, const string& filename);
+
+unsigned int getFileSize(const string& path);
+string getFileSizeAsString(const string& path);
+string getFileContent(const string& path);
+bool fileExists(const string& path);
+bool makeDirectory(const string& path);
+string makeTmpDirectory();
+bool copyFile(const string& sourcePath, const string& destPath);
+string getLastPathElement(const string& path);
+string getExecutablePath();
+string getCurrentDirectory();
+string getDataDirectory();
+bool writeTextFile(const string& path, const string& content);
+#endif

include/common/regexTools.h

@@ -20,6 +20,9 @@
 #ifndef KIWIX_REGEXTOOLS_H
 #define KIWIX_REGEXTOOLS_H
 
+#include <unicode/regex.h>
+#include <unicode/ucnv.h>
+#include <map>
 #include <string>
 
 bool matchRegex(const std::string& content, const std::string& regex);
@@ -27,7 +30,7 @@ std::string replaceRegex(const std::string& content,
                          const std::string& replacement,
                          const std::string& regex);
 std::string appendToFirstOccurence(const std::string& content,
-                                   const std::string& regex,
+                                   const std::string regex,
                                    const std::string& replacement);
 
 #endif

include/common/stringTools.h

@@ -22,12 +22,19 @@
 
 #include <unicode/unistr.h>
 
+#include <fstream>
+#include <iomanip>
+#include <iostream>
+#include <sstream>
 #include <string>
 #include <vector>
-#include <sstream>
+
+#include "pathTools.h"
 
 namespace kiwix
 {
+#ifndef __ANDROID__
+
 std::string beautifyInteger(uint64_t number);
 std::string beautifyFileSize(uint64_t number);
 void printStringInHexadecimal(const char* s);
@@ -37,14 +44,18 @@ void stringReplacement(std::string& str,
                        const std::string& newStr);
 std::string encodeDiples(const std::string& str);
 
+#endif
+
 std::string removeAccents(const std::string& text);
 void loadICUExternalTables();
 
 std::string urlEncode(const std::string& value, bool encodeReserved = false);
 std::string urlDecode(const std::string& value, bool component = false);
 
-std::vector<std::string> split(const std::string&, const std::string&, bool trimEmpty = true);
-std::string join(const std::vector<std::string>& list, const std::string& sep);
+std::vector<std::string> split(const std::string&, const std::string&);
+std::vector<std::string> split(const char*, const char*);
+std::vector<std::string> split(const std::string&, const char*);
+std::vector<std::string> split(const char*, const std::string&);
 
 std::string ucAll(const std::string& word);
 std::string lcAll(const std::string& word);
@@ -68,7 +79,5 @@ T extractFromString(const std::string& str) {
     iss >> ret;
     return ret;
 }
-
-bool startsWith(const std::string& base, const std::string& start);
 } //namespace kiwix
 #endif

include/ctpp2/CTPP2VMStringLoader.hpp

@@ -0,0 +1,79 @@
+/*
+ * Copyright 2013 Renaud Gaudin <reg@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef _CTPP2_VM_STRING_LOADER_HPP__
+#define _CTPP2_VM_STRING_LOADER_HPP__ 1
+
+#include <ctpp2/CTPP2VMLoader.hpp>
+#include <ctpp2/CTPP2Util.hpp>
+#include <ctpp2/CTPP2Exception.hpp>
+#include <ctpp2/CTPP2VMExecutable.hpp>
+#include <ctpp2/CTPP2VMInstruction.hpp>
+#include <ctpp2/CTPP2VMMemoryCore.hpp>
+
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <iostream>
+#include <string>
+
+/**
+  @file VMStringLoader.hpp
+  @brief Load program core from file
+*/
+
+namespace CTPP // C++ Template Engine
+{
+// FWD
+struct VMExecutable;
+
+/**
+  @class VMStringLoader CTPP2VMStringLoader.hpp <CTPP2VMStringLoader.hpp>
+  @brief Load program core from file
+*/
+class CTPP2DECL VMStringLoader:
+  public VMLoader
+{
+public:
+	/**
+	*/
+	VMStringLoader(CCHAR_P rawContent, size_t rawContentSize);
+	/**
+	  @brief Get ready-to-run program
+	*/
+	const VMMemoryCore * GetCore() const;
+
+	/**
+	  @brief A destructor
+	*/
+	~VMStringLoader() throw();
+private:
+	/** Program core             */
+	VMExecutable  * oCore;
+	/** Ready-to-run program     */
+	VMMemoryCore  * pVMMemoryCore;
+};
+
+} // namespace CTPP
+#endif // _CTPP2_VM_STRING_LOADER_HPP__
+// End.

include/downloader.h

@@ -54,9 +54,6 @@ class Download {
       m_status(K_UNKNOWN),
       m_did(did) {};
   void updateStatus(bool follow=false);
-  void pauseDownload();
-  void resumeDownload();
-  void cancelDownload();
   StatusResult getStatus()          { return m_status; }
   std::string  getDid()             { return m_did; }
   std::string  getFollowedBy()      { return m_followedBy; }
@@ -97,7 +94,6 @@ class Downloader
 
   size_t getNbDownload() { return m_knownDownloads.size(); }
   std::vector<std::string> getDownloadIds();
-  const std::string &getAria2LaunchCmd();
 
  private:
   std::map<std::string, std::unique_ptr<Download>> m_knownDownloads;

include/entry.h

@@ -24,7 +24,6 @@
 #include <zim/article.h>
 #include <exception>
 #include <string>
-
 #include "common.h"
 
 using namespace std;
@@ -64,14 +63,14 @@ class Entry
      * @return the path of the entry.
      */
     std::string getPath() const;
-
+    
     /**
      * Get the title of the entry.
      *
      * @return the title of the entry.
      */
     std::string getTitle() const;
-
+        
     /**
      * Get the content of the entry.
      *
@@ -81,7 +80,7 @@ class Entry
      * @return the content of the entry.
      */
     std::string getContent() const;
-
+        
     /**
      * Get the blob of the entry.
      *
@@ -91,7 +90,7 @@ class Entry
      * @return the blob of the entry.
      */
     zim::Blob   getBlob(offset_type offset = 0) const;
-
+        
     /**
      * Get the blob of the entry.
      *
@@ -102,7 +101,7 @@ class Entry
      * @return the blob of the entry.
      */
     zim::Blob   getBlob(offset_type offset, size_type size) const;
-
+        
     /**
      * Get the info for direct access to the content of the entry.
      *
@@ -118,7 +117,7 @@ class Entry
      *         Return <"",0> if is not possible to read directly.
      */
     std::pair<std::string, offset_type> getDirectAccessInfo() const;
-
+        
     /**
      * Get the size of the entry.
      *
@@ -132,8 +131,8 @@ class Entry
      * @return the mime_type of the entry.
      */
     std::string getMimetype() const;
-
-
+    
+    
     /**
      * Get if the entry is a redirect entry.
      *

include/kiwixserve.h

@@ -1,30 +0,0 @@
-#ifndef KIWIXLIB_KIWIX_SERVE_H_
-#define KIWIXLIB_KIWIX_SERVE_H_
-
-#include <memory>
-#include <string>
-
-class Subprocess;
-namespace kiwix {
-
-class KiwixServe
-{
-  public:
-    KiwixServe(const std::string& libraryPath, int port = 8181);
-    ~KiwixServe();
-
-    void run();
-    void shutDown();
-    bool isRunning();
-    int getPort() { return m_port; }
-    int setPort(int port);
-
-  private:
-  std::unique_ptr<Subprocess> mp_kiwixServe;
-  int m_port;
-  std::string m_libraryPath;
-};
-
-}; //end namespace kiwix
-
-#endif // KIWIXLIB_KIWIX_SERVE_H_

include/library.h

@@ -23,17 +23,13 @@
 #include <string>
 #include <vector>
 #include <map>
-#include <memory>
-
-#include "book.h"
-#include "bookmark.h"
-#include "common.h"
 
 #define KIWIX_LIBRARY_VERSION "20110515"
 
 namespace kiwix
 {
 
+class Book;
 class OPDSDumper;
 
 enum supportedListSortBy { UNSORTED, TITLE, SIZE, DATE, CREATOR, PUBLISHER };
@@ -46,78 +42,17 @@ enum supportedListMode {
   VALID = 1 << 4,
   NOVALID = 1 << 5
 };
-
-class Filter {
-  private:
-    uint64_t activeFilters;
-    std::vector<std::string> _acceptTags;
-    std::vector<std::string> _rejectTags;
-    std::string _lang;
-    std::string _publisher;
-    std::string _creator;
-    size_t _maxSize;
-    std::string _query;
-
-  public:
-    Filter();
-    ~Filter() = default;
-
-    /**
-     *  Set the filter to check local.
-     *
-     *  A local book is a book with a path.
-     *  If accept is true, only local book are accepted.
-     *  If accept is false, only non local book are accepted.
-     */
-    Filter& local(bool accept);
-
-    /**
-     *  Set the filter to check remote.
-     *
-     *  A remote book is a book with a url.
-     *  If accept is true, only remote book are accepted.
-     *  If accept is false, only non remote book are accepted.
-     */
-    Filter& remote(bool accept);
-
-    /**
-     *  Set the filter to check validity.
-     *
-     *  A valid book is a book with a path pointing to a existing zim file.
-     *  If accept is true, only valid book are accepted.
-     *  If accept is false, only non valid book are accepted.
-     */
-    Filter& valid(bool accept);
-
-    /**
-     * Set the filter to only accept book with corresponding tag.
-     */
-    Filter& acceptTags(std::vector<std::string> tags);
-    Filter& rejectTags(std::vector<std::string> tags);
-
-    Filter& lang(std::string lang);
-    Filter& publisher(std::string publisher);
-    Filter& creator(std::string creator);
-    Filter& maxSize(size_t size);
-    Filter& query(std::string query);
-
-    bool accept(const Book& book) const;
-};
-
-
 /**
  * A Library store several books.
  */
 class Library
 {
-  std::map<std::string, kiwix::Book> m_books;
-  std::map<std::string, std::shared_ptr<Reader>> m_readers;
-  std::vector<kiwix::Bookmark> m_bookmarks;
-
+  std::map<std::string, kiwix::Book> books;
  public:
   Library();
   ~Library();
 
+  std::string version;
   /**
    * Add a book to the library.
    *
@@ -130,24 +65,7 @@ class Library
    */
   bool addBook(const Book& book);
 
-  /**
-   * Add a bookmark to the library.
-   *
-   * @param bookmark the book to add.
-   */
-  void addBookmark(const Bookmark& bookmark);
-
-  /**
-   * Remove a bookmarkk
-   *
-   * @param zimId The zimId of the bookmark.
-   * @param url The url of the bookmark.
-   * @return True if the bookmark has been removed.
-   */
-  bool removeBookmark(const std::string& zimId, const std::string& url);
-
   Book& getBookById(const std::string& id);
-  std::shared_ptr<Reader> getReaderById(const std::string& id);
 
   /**
    * Remove a book from the library.
@@ -161,18 +79,10 @@ class Library
    * Write the library to a file.
    *
    * @param path the path of the file to write to.
-   * @return True if the library has been correctly saved.
+   * @return True if the library has been correctly save.
    */
   bool writeToFile(const std::string& path);
 
-  /**
-   * Write the library bookmarks to a file.
-   *
-   * @param path the path of the file to write to.
-   * @return True if the library has been correctly saved.
-   */
-  bool writeBookmarksToFile(const std::string& path);
-
   /**
    * Get the number of book in the library.
    *
@@ -203,13 +113,6 @@ class Library
    */
   std::vector<std::string> getBooksPublishers();
 
-  /**
-   * Get all bookmarks.
-   *
-   * @return A list of bookmarks
-   */
-  const std::vector<kiwix::Bookmark> getBookmarks(bool onlyValidBookmarks = true);
-
   /**
    * Get all book ids of the books in the library.
    *
@@ -225,27 +128,9 @@ class Library
    * @param search List only books with search in the title or description.
    * @return The list of bookIds corresponding to the query.
    */
-  DEPRECATED std::vector<std::string> filter(const std::string& search);
+  std::vector<std::string> filter(const std::string& search);
 
 
-  /**
-   * Filter the library and return the id of the keep elements.
-   *
-   * @param filter The filter to use.
-   * @return The list of bookIds corresponding to the filter.
-   */
-  std::vector<std::string> filter(const Filter& filter);
-
-
-  /**
-   * Sort (in place) bookIds using the given comparator.
-   *
-   * @param bookIds the list of book Ids to sort
-   * @param comparator how to sort the books
-   * @return The sorted list of books
-   */
-  void sort(std::vector<std::string>& bookIds, supportedListSortBy sortBy, bool ascending);
-
   /**
    * List books in the library.
    *
@@ -268,18 +153,16 @@ class Library
    *                Set to 0 to cancel this filter.
    * @return The list of bookIds corresponding to the query.
    */
-  DEPRECATED std::vector<std::string> listBooksIds(
+  std::vector<std::string> listBooksIds(
     int supportedListMode = ALL,
     supportedListSortBy sortBy = UNSORTED,
     const std::string& search = "",
     const std::string& language = "",
     const std::string& creator = "",
     const std::string& publisher = "",
-    const std::vector<std::string>& tags = {},
     size_t maxSize = 0);
 
   friend class OPDSDumper;
-  friend class libXMLDumper;
 };
 }
 

include/libxml_dumper.h

@@ -1,83 +0,0 @@
-/*
- * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_LIBXML_DUMPER_H
-#define KIWIX_LIBXML_DUMPER_H
-
-#include <string>
-#include <vector>
-
-#include <pugixml.hpp>
-
-#include "library.h"
-
-namespace kiwix
-{
-
-/**
- * A tool to dump a `Library` into a basic library.xml
- *
- */
-class LibXMLDumper
-{
- public:
-  LibXMLDumper() = default;
-  LibXMLDumper(Library* library);
-  ~LibXMLDumper();
-
-  /**
-   * Dump the library.xml
-   *
-   * @param id The id of the library.
-   * @return The library.xml content.
-   */
-  std::string dumpLibXMLContent(const std::vector<std::string>& bookIds);
-
-
-  /**
-   * Dump the bookmark of the library.
-   *
-   * @return The bookmark.xml content.
-   */
-  std::string dumpLibXMLBookmark();
-
-  /**
-   * Set the base directory used.
-   *
-   * @param baseDir the base directory to use.
-   */
-  void setBaseDir(const std::string& baseDir) { this->baseDir = baseDir; }
-
-  /**
-   * Set the library to dump.
-   *
-   * @param library The library to dump.
-   */
-  void setLibrary(Library* library) { this->library = library; }
-
- protected:
-  kiwix::Library* library;
-  std::string baseDir;
- private:
-  void handleBook(Book book, pugi::xml_node root_node);
-  void handleBookmark(Bookmark bookmark, pugi::xml_node root_node);
-};
-}
-
-#endif // KIWIX_OPDS_DUMPER_H

include/manager.h

@@ -38,7 +38,6 @@ class LibraryManipulator {
  public:
   virtual ~LibraryManipulator() {}
   virtual bool addBookToLibrary(Book book) = 0;
-  virtual void addBookmarkToLibrary(Bookmark bookmark) = 0;
 };
 
 class DefaultLibraryManipulator : public LibraryManipulator {
@@ -49,15 +48,15 @@ class DefaultLibraryManipulator : public LibraryManipulator {
   bool addBookToLibrary(Book book) {
     return library->addBook(book);
   }
-  void addBookmarkToLibrary(Bookmark bookmark) {
-    library->addBookmark(bookmark);
-  }
  private:
    kiwix::Library* library;
 };
 
 /**
  * A tool to manage a `Library`.
+ *
+ * A `Manager` handle a internal `Library`.
+ * This `Library` can be retrived with `cloneLibrary` method.
  */
 class Manager
 {
@@ -114,15 +113,6 @@ class Manager
    */
   bool readOpds(const std::string& content, const std::string& urlHost);
 
-
-  /**
-   * Load a bookmark file.
-   *
-   * @param path The path of the file to read.
-   * @return True if the content has been properly parsed.
-   */
-  bool readBookmarkFile(const std::string& path);
-
   /**
    * Add a book to the library.
    *
@@ -155,6 +145,55 @@ class Manager
                        const std::string& url = "",
                        const bool checkMetaData = false);
 
+  /**
+   * Get the book corresponding to an id.
+   *
+   * @param[in] id The id of the book
+   * @param[out] book The book corresponding to the id.
+   * @return True if the book has been found.
+   */
+  bool getBookById(const std::string& id, Book& book);
+
+  /**
+   * Update the "last open date" of a book
+   *
+   * @param id the id of the book.
+   * @return True if the book is in the library.
+   */
+  bool updateBookLastOpenDateById(const std::string& id);
+
+  /**
+   * Remove (set to empty) paths of all books in the library.
+   */
+  void removeBookPaths();
+
+  /**
+   * List books in the library.
+   *
+   * The books list will be available in public vector member `bookIdList`.
+   *
+   * @param mode The mode of listing :
+   *             - LASTOPEN sort by last opened book.
+   *             - LOCAL list only local file.
+   *             - REMOTE list only remote file.
+   * @param sortBy Attribute to sort by the book list.
+   * @param maxSize Do not list book bigger than maxSize MiB.
+   *                Set to 0 to cancel this filter.
+   * @param language List only books in this language.
+   * @param creator List only books of this creator.
+   * @param publisher List only books of this publisher.
+   * @param search List only books with search in the title, description or
+   *               language.
+   * @return True
+   */
+  bool listBooks(const supportedListMode mode,
+                 const supportedListSortBy sortBy,
+                 const unsigned int maxSize,
+                 const std::string& language,
+                 const std::string& creator,
+                 const std::string& publisher,
+                 const std::string& search);
+
   std::string writableLibraryPath;
 
   bool m_hasSearchResult = false;
@@ -173,6 +212,8 @@ class Manager
   bool parseOpdsDom(const pugi::xml_document& doc,
                     const std::string& urlHost);
 
+ private:
+  void checkAndCleanBookPaths(Book& book, const std::string& libraryPath);
 };
 }
 

include/meson.build

@@ -1,31 +1,35 @@
 headers = [
   'book.h',
-  'bookmark.h',
   'common.h',
   'library.h',
   'manager.h',
-  'libxml_dumper.h',
   'opds_dumper.h',
   'downloader.h',
   'reader.h',
   'entry.h',
-  'searcher.h',
-  'search_renderer.h',
-  'server.h',
-  'kiwixserve.h',
-  'name_mapper.h'
+  'searcher.h'
 ]
 
+if xapian_dep.found()
+  headers += ['xapianSearcher.h']
+endif
+
 install_headers(headers, subdir:'kiwix')
 
 install_headers(
-  'tools/base64.h',
-  'tools/networkTools.h',
-  'tools/otherTools.h',
-  'tools/pathTools.h',
-  'tools/regexTools.h',
-  'tools/stringTools.h',
-  'tools/lock.h',
-  subdir:'kiwix/tools'
+  'common/base64.h',
+  'common/networkTools.h',
+  'common/otherTools.h',
+  'common/pathTools.h',
+  'common/regexTools.h',
+  'common/stringTools.h',
+  subdir:'kiwix/common'
 )
 
+if has_ctpp2_dep
+  install_headers(
+    'ctpp2/CTPP2VMStringLoader.hpp',
+    subdir:'kiwix/ctpp2'
+  )
+endif
+

include/name_mapper.h

@@ -1,61 +0,0 @@
-/*
- * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_NAMEMAPPER_H
-#define KIWIX_NAMEMAPPER_H
-
-#include <string>
-#include <map>
-
-namespace kiwix
-{
-
-class Library;
-
-class NameMapper {
-  public:
-    virtual ~NameMapper() = default;
-    virtual std::string getNameForId(const std::string& id) = 0;
-    virtual std::string getIdForName(const std::string& name) = 0;
-};
-
-
-class IdNameMapper : public NameMapper {
-  public:
-    virtual std::string getNameForId(const std::string& id) { return id; };
-    virtual std::string getIdForName(const std::string& name) { return name; };
-};
-
-class HumanReadableNameMapper : public NameMapper {
-  private:
-    std::map<std::string, std::string> m_idToName;
-    std::map<std::string, std::string> m_nameToId;
-
-  public:
-    HumanReadableNameMapper(kiwix::Library& library, bool withAlias);
-    virtual ~HumanReadableNameMapper() = default;
-    virtual std::string getNameForId(const std::string& id);
-    virtual std::string getIdForName(const std::string& name);
-};
-
-
-
-}
-
-#endif

include/opds_dumper.h

@@ -26,9 +26,9 @@
 
 #include <pugixml.hpp>
 
-#include "tools/base64.h"
-#include "tools/pathTools.h"
-#include "tools/regexTools.h"
+#include "common/base64.h"
+#include "common/pathTools.h"
+#include "common/regexTools.h"
 #include "library.h"
 #include "reader.h"
 

include/reader.h

@@ -31,8 +31,8 @@
 #include <string>
 #include "common.h"
 #include "entry.h"
-#include "tools/pathTools.h"
-#include "tools/stringTools.h"
+#include "common/pathTools.h"
+#include "common/stringTools.h"
 
 using namespace std;
 
@@ -158,14 +158,7 @@ class Reader
    * @param[out] value The value will be set to the content of the metadata.
    * @return True if it was possible to get the content of the metadata.
    */
-  bool getMetadata(const string& name, string& value) const;
-
-  /**
-   * Get the name of the zim file.
-   *
-   * @return The name of the zim file as specified in the zim metadata.
-   */
-  string getName() const;
+  bool getMetatag(const string& name, string& value) const;
 
   /**
    * Get the title of the zim file.
@@ -176,6 +169,42 @@ class Reader
    */
   string getTitle() const;
 
+  /**
+   * Get the description of the zim file.
+   *
+   * @return The description of the zim file as specified in the zim metadata.
+   *         If no description has been set, return the subtitle.
+   */
+  string getDescription() const;
+
+  /**
+   * Get the language of the zim file.
+   *
+   * @return The language of the zim file as specified in the zim metadata.
+   */
+  string getLanguage() const;
+
+  /**
+   * Get the name of the zim file.
+   *
+   * @return The name of the zim file as specified in the zim metadata.
+   */
+  string getName() const;
+
+  /**
+   * Get the tags of the zim file.
+   *
+   * @return The tags of the zim file as specified in the zim metadata.
+   */
+  string getTags() const;
+
+  /**
+   * Get the date of the zim file.
+   *
+   * @return The date of the zim file as specified in the zim metadata.
+   */
+  string getDate() const;
+
   /**
    * Get the creator of the zim file.
    *
@@ -190,100 +219,6 @@ class Reader
    */
   string getPublisher() const;
 
-  /**
-   * Get the date of the zim file.
-   *
-   * @return The date of the zim file as specified in the zim metadata.
-   */
-  string getDate() const;
-
-  /**
-   * Get the description of the zim file.
-   *
-   * @return The description of the zim file as specified in the zim metadata.
-   *         If no description has been set, return the subtitle.
-   */
-  string getDescription() const;
-
-  /**
-   * Get the long description of the zim file.
-   *
-   * @return The long description of the zim file as specifed in the zim metadata.
-   */
-  string getLongDescription() const;
-
-  /**
-   * Get the language of the zim file.
-   *
-   * @return The language of the zim file as specified in the zim metadata.
-   */
-  string getLanguage() const;
-
-  /**
-   * Get the license of the zim file.
-   *
-   * @return The license of the zim file as specified in the zim metadata.
-   */
-  string getLicense() const;
-
-  /**
-   * Get the tags of the zim file.
-   *
-   * @param original If true, return the original tags as specified in the zim metadata.
-   *                 Else, try to convert it to the new 'normalized' format.
-   * @return The tags of the zim file.
-   */
-  string getTags(bool original=false) const;
-
-  /**
-   * Get the value (as a string) of a specific tag.
-   *
-   * According to https://wiki.openzim.org/wiki/Tags
-   *
-   * @return The value of the specified tag.
-   * @throw  std::out_of_range if the specified tag is not found.
-   */
-  string getTagStr(const std::string& tagName) const;
-
-  /**
-   * Get the boolean value of a specific tag.
-   *
-   * According to https://wiki.openzim.org/wiki/Tags
-   *
-   * @return The boolean value of the specified tag.
-   * @throw  std::out_of_range if the specified tag is not found.
-   *         std::domain_error if the value of the tag cannot be convert to bool.
-   */
-  bool getTagBool(const std::string& tagName) const;
-
-  /**
-   * Get the relations of the zim file.
-   *
-   * @return The relation of the zim file as specified in the zim metadata.
-   */
-  string getRelation() const;
-
-  /**
-   * Get the flavour of the zim file.
-   *
-   * @return The flavour of the zim file as specified in the zim metadata.
-   */
-  string getFlavour() const;
-
-  /**
-   * Get the source of the zim file.
-   *
-   * @return The source of the zim file as specified in the zim metadata.
-   */
-  string getSource() const;
-
-  /**
-   * Get the scraper of the zim file.
-   *
-   * @return The scraper of the zim file as specified in the zim metadata.
-   */
-  string getScraper() const;
-
   /**
    * Get the origId of the zim file.
    *

include/search_renderer.h

@@ -1,85 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_SEARCH_RENDERER_H
-#define KIWIX_SEARCH_RENDERER_H
-
-#include <string>
-
-namespace kiwix
-{
-
-class Searcher;
-class NameMapper;
-/**
- * The SearcherRenderer class is used to render a search result to a html page.
- */
-class SearchRenderer
-{
- public:
-  /**
-   * The default constructor.
-   *
-   * @param humanReadableName The global zim's humanReadableName.
-   *                          Used to generate pagination links.
-   */
-  SearchRenderer(Searcher* searcher, NameMapper* mapper);
-
-  ~SearchRenderer();
-
-  void setSearchPattern(const std::string& pattern);
-
-  /**
-   * Set the search content id.
-   */
-  void setSearchContent(const std::string& name);
-
-  /**
-   * Set protocol prefix.
-   */
-  void setProtocolPrefix(const std::string& prefix);
-
-  /**
-   * Set search protocol prefix.
-   */
-  void setSearchProtocolPrefix(const std::string& prefix);
-
-  /**
-   * Generate the html page with the resutls of the search.
-   */
-  std::string getHtml();
-
- protected:
-  std::string beautifyInteger(const unsigned int number);
-  Searcher* mp_searcher;
-  NameMapper* mp_nameMapper;
-  std::string searchContent;
-  std::string searchPattern;
-  std::string protocolPrefix;
-  std::string searchProtocolPrefix;
-  unsigned int resultCountPerPage;
-  unsigned int estimatedResultCount;
-  unsigned int resultStart;
-  unsigned int resultEnd;
-};
-
-
-}
-
-#endif

include/searcher.h

@@ -29,8 +29,8 @@
 #include <string>
 #include <vector>
 #include <vector>
-#include "tools/pathTools.h"
-#include "tools/stringTools.h"
+#include "common/pathTools.h"
+#include "common/stringTools.h"
 #include "kiwix_config.h"
 
 using namespace std;
@@ -56,28 +56,65 @@ struct SearcherInternal;
 /**
  * The Searcher class is reponsible to do different kind of search using the
  * fulltext index.
+ *
+ * Historically, there are two kind of fulltext index :
+ *  - The legacy one, is the external fulltext index. A directory stored outside
+ *    of the zim file.
+ *  - The new one, a embedded fulltext index in the zim file.
+ *
+ * Legacy external fulltext index has to be considered as obsolet format with
+ * less functionnalities:
+ *  - No multi zim search ;
+ *  - No geo_search ;
+ *  - No suggestions search ;
+ *
+ * To reflect this, there is two Search creation "API":
+ *  - One for the external fulltext index, using the constructor taking a
+ *    xapianDirectoryPath) ;
+ *  - One for the embedded fulltext index, using a "empty" constructor and the
+ *  `add_reader` method".
+ *
+ *  On top of that, the Searcher may (if compiled with ctpp2) be used to
+ *  generate a html page for the search result. This use a template that need a
+ *  humanReaderName. This feature is only used by kiwix-serve and this should be
+ *  move outside of Searcher (and with a better API). If you don't use the html
+ *  rendering (getHtml method), you better should simply ignore the different
+ *  humanReadeableName attributes (or give an empty string).
  */
 class Searcher
 {
  public:
   /**
    * The default constructor.
+   *
+   * @param humanReadableName The global zim's humanReadableName.
+   *                          Used to generate pagination links.
    */
-  Searcher();
+  Searcher(const string& humanReadableName = "");
 
+  /**
+   * The constructor for legacy external fulltext index.
+   *
+   * @param xapianDirectoryPath The path to the external index directory.
+   * @param reader The reader associated to the external index.
+   *               It will be used retrive the article content or generate
+   *               the snippet.
+   * @param humanReadableName The humanReadableName for the zim.
+   */
+  Searcher(const string& xapianDirectoryPath,
+           Reader* reader,
+           const string& humanReadableName);
   ~Searcher();
 
   /**
    * Add a reader (containing embedded fulltext index) to the search.
    *
    * @param reader The Reader for the zim containing the fulltext index.
+   * @param humanReaderName The human readable name of the reader.
    * @return true if the reader has been added.
    *         false if the reader cannot be added (no embedded fulltext index present)
    */
-  bool add_reader(Reader* reader);
-
-
-  Reader* get_reader(int index);
+  bool add_reader(Reader* reader, const std::string& humanReaderName);
 
   /**
    * Start a search on the zim associated to the Searcher.
@@ -143,8 +180,24 @@ class Searcher
    */
   unsigned int getEstimatedResultCount();
 
-  unsigned int getResultStart() { return resultStart; }
-  unsigned int getResultEnd() { return resultEnd; }
+  /**
+   * Set protocol prefix.
+   * Only used by getHtml.
+   */
+  bool setProtocolPrefix(const std::string prefix);
+
+  /**
+   * Set search protocol prefix.
+   * Only used by getHtml.
+   */
+  bool setSearchProtocolPrefix(const std::string prefix);
+
+#ifdef ENABLE_CTPP2
+  /**
+   * Generate the html page with the resutls of the search.
+   */
+  string getHtml();
+#endif
 
  protected:
   std::string beautifyInteger(const unsigned int number);
@@ -155,11 +208,16 @@ class Searcher
                      const bool verbose = false);
 
   std::vector<Reader*> readers;
+  std::vector<std::string> humanReaderNames;
   SearcherInternal* internal;
   std::string searchPattern;
+  std::string protocolPrefix;
+  std::string searchProtocolPrefix;
+  unsigned int resultCountPerPage;
   unsigned int estimatedResultCount;
   unsigned int resultStart;
   unsigned int resultEnd;
+  std::string contentHumanReadableId;
 
  private:
   void reset();

include/server.h

@@ -1,75 +0,0 @@
-/*
- * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_SERVER_H
-#define KIWIX_SERVER_H
-
-#include <string>
-#include <memory>
-
-namespace kiwix
-{
-  class Library;
-  class NameMapper;
-  class InternalServer;
-
-  class Server {
-     public:
-       /**
-        * The default constructor.
-        *
-        * @param library The library to serve.
-        */
-       Server(Library* library, NameMapper* nameMapper=nullptr);
-
-       virtual ~Server();
-
-       /**
-        * Serve the content.
-        */
-       bool start();
-
-       /**
-        * Stop the daemon.
-        */
-       void stop();
-
-       void setRoot(const std::string& root);
-       void setAddress(const std::string& addr) { m_addr = addr; }
-       void setPort(int port) { m_port = port; }
-       void setNbThreads(int threads) { m_nbThreads = threads; }
-       void setVerbose(bool verbose) { m_verbose = verbose; }
-       void setTaskbar(bool withTaskbar, bool withLibraryButton)
-         { m_withTaskbar = withTaskbar; m_withLibraryButton = withLibraryButton; }
-
-     protected:
-       Library* mp_library;
-       NameMapper* mp_nameMapper;
-       std::string m_root = "";
-       std::string m_addr = "";
-       int m_port = 80;
-       int m_nbThreads = 1;
-       bool m_verbose = false;
-       bool m_withTaskbar = true;
-       bool m_withLibraryButton = true;
-       std::unique_ptr<InternalServer> mp_server;
-  };
-}
-
-#endif

include/tools/lock.h

@@ -1,46 +0,0 @@
-
-
-#ifndef KIWIXLIB_TOOL_LOCK_H
-#define KIWIXLIB_TOOL_LOCK_H
-
-#include <pthread.h>
-
-namespace kiwix {
-
-class Lock
-{
-  public:
-    explicit Lock(pthread_mutex_t* mutex) :
-      mp_mutex(mutex)
-    {
-      pthread_mutex_lock(mp_mutex);
-    }
-    ~Lock() {
-      if (mp_mutex != nullptr) {
-        pthread_mutex_unlock(mp_mutex);
-      }
-    }
-    Lock(Lock && other) :
-      mp_mutex(other.mp_mutex)
-    {
-      other.mp_mutex = nullptr;
-    }
-    Lock & operator=(Lock && other)
-    {
-      mp_mutex = other.mp_mutex;
-      other.mp_mutex = nullptr;
-      return *this;
-    }
-
-
-  private:
-    pthread_mutex_t* mp_mutex;
-
-    Lock(Lock const &) = delete;
-    Lock & operator=(Lock const &) = delete;
-};
-
-
-}
-
-#endif //KIWIXLIB_TOOL_LOCK_H

include/tools/pathTools.h

@@ -1,44 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_PATHTOOLS_H
-#define KIWIX_PATHTOOLS_H
-
-#include <string>
-
-bool isRelativePath(const std::string& path);
-std::string computeAbsolutePath(const std::string& path, const std::string& relativePath);
-std::string computeRelativePath(const std::string& path, const std::string& absolutePath);
-std::string removeLastPathElement(const std::string& path);
-std::string appendToDirectory(const std::string& directoryPath, const std::string& filename);
-
-unsigned int getFileSize(const std::string& path);
-std::string getFileSizeAsString(const std::string& path);
-std::string getFileContent(const std::string& path);
-bool fileExists(const std::string& path);
-bool makeDirectory(const std::string& path);
-std::string makeTmpDirectory();
-bool copyFile(const std::string& sourcePath, const std::string& destPath);
-std::string getLastPathElement(const std::string& path);
-std::string getExecutablePath(bool realPathOnly = false);
-std::string getCurrentDirectory();
-std::string getDataDirectory();
-bool writeTextFile(const std::string& path, const std::string& content);
-std::string getMimeTypeForFile(const std::string& filename);
-#endif

include/xapianSearcher.h

@@ -0,0 +1,98 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_XAPIAN_SEARCHER_H
+#define KIWIX_XAPIAN_SEARCHER_H
+
+#include <xapian.h>
+#include "reader.h"
+#include "searcher.h"
+
+#include <map>
+#include <string>
+
+using namespace std;
+
+namespace kiwix
+{
+class XapianSearcher;
+
+class XapianResult : public Result
+{
+ public:
+  XapianResult(XapianSearcher* searcher, Xapian::MSetIterator& iterator);
+  virtual ~XapianResult(){};
+
+  virtual std::string get_url();
+  virtual std::string get_title();
+  virtual int get_score();
+  virtual std::string get_snippet();
+  virtual std::string get_content();
+  virtual int get_wordCount();
+  virtual int get_size();
+  virtual int get_readerIndex() { return 0; };
+
+ private:
+  XapianSearcher* searcher;
+  Xapian::MSetIterator iterator;
+  Xapian::Document document;
+};
+
+class NoXapianIndexInZim : public exception
+{
+  virtual const char* what() const throw()
+  {
+    return "There is no fulltext index in the zim file";
+  }
+};
+
+class XapianSearcher
+{
+  friend class XapianResult;
+
+ public:
+  XapianSearcher(const string& xapianDirectoryPath, Reader* reader);
+  virtual ~XapianSearcher(){};
+  void searchInIndex(string& search,
+                     const unsigned int resultStart,
+                     const unsigned int resultEnd,
+                     const bool verbose = false);
+  virtual Result* getNextResult();
+  void restart_search();
+
+  Xapian::MSet results;
+
+ protected:
+  void closeIndex();
+  void openIndex(const string& xapianDirectoryPath);
+  void setup_queryParser();
+
+  Reader* reader;
+  Xapian::Database readableDatabase;
+  std::string language;
+  std::string stopwords;
+  Xapian::QueryParser queryParser;
+  Xapian::Stem stemmer;
+  Xapian::SimpleStopper stopper;
+  Xapian::MSetIterator current_result;
+  std::map<std::string, int> valuesmap;
+};
+}
+
+#endif

meson.build

@@ -1,9 +1,10 @@
 project('kiwix-lib', 'cpp',
-  version : '8.2.2', # Also change this in android-kiwix-lib-publisher/kiwixLibAndroid/build.gradle
+  version : '3.0.3',
   license : 'GPL',
   default_options : ['c_std=c11', 'cpp_std=c++11', 'werror=true'])
 
 compiler = meson.get_compiler('cpp')
+find_library_in_compiler = meson.version().version_compare('>=0.31.0')
 
 static_deps = get_option('android') or get_option('default_library') == 'static'
 if get_option('android')
@@ -14,14 +15,9 @@ endif
 
 thread_dep = dependency('threads')
 libicu_dep = dependency('icu-i18n', static:static_deps)
-libzim_dep = dependency('libzim', version : '>=5.0.0', static:static_deps)
+libzim_dep = dependency('libzim', version : '>=4.0.0', static:static_deps)
 pugixml_dep = dependency('pugixml', static:static_deps)
 libcurl_dep = dependency('libcurl', static:static_deps)
-microhttpd_dep = dependency('libmicrohttpd', static:static_deps)
-
-if not compiler.has_header('mustache.hpp')
-  error('Cannot found header mustache.hpp')
-endif
 
 extra_cflags = ''
 if target_machine.system() == 'windows' and static_deps
@@ -29,12 +25,77 @@ if target_machine.system() == 'windows' and static_deps
   extra_cflags += '-DCURL_STATICLIB'
 endif
 
-all_deps = [thread_dep, libicu_dep, libzim_dep, pugixml_dep, libcurl_dep, microhttpd_dep]
+
+
+ctpp2_include_path = ''
+has_ctpp2_dep = false
+ctpp2_prefix_install = get_option('ctpp2-install-prefix')
+ctpp2_link_args = []
+if ctpp2_prefix_install == ''
+  if compiler.has_header('ctpp2/CTPP2Logger.hpp')
+    if find_library_in_compiler
+      ctpp2_lib = compiler.find_library('ctpp2')
+    else
+      ctpp2_lib = find_library('ctpp2')
+    endif
+    ctpp2_link_args = ['-lctpp2']
+    if meson.is_cross_build() and host_machine.system() == 'windows'
+      if find_library_in_compiler
+        iconv_lib = compiler.find_library('iconv', required:false)
+      else
+        iconv_lib = find_library('iconv', required:false)
+      endif
+      if iconv_lib.found()
+        ctpp2_link_args += ['-liconv']
+      endif
+    endif
+    has_ctpp2_dep = true
+    ctpp2_dep = declare_dependency(link_args:ctpp2_link_args)
+  else
+    message('ctpp2/CTPP2Logger.hpp not found. Compiling without CTPP2 support')
+  endif
+else
+  if not find_library_in_compiler
+    error('For custom ctpp2_prefix_install you need a meson version >=0.31.0')
+  endif
+  ctpp2_include_path = ctpp2_prefix_install + '/include'
+  ctpp2_include_args = ['-I'+ctpp2_include_path]
+  if compiler.has_header('ctpp2/CTPP2Logger.hpp', args:ctpp2_include_args)
+    ctpp2_include_dir = include_directories(ctpp2_include_path, is_system:true)
+    ctpp2_lib_path = join_paths(ctpp2_prefix_install, get_option('libdir'))
+    message(ctpp2_lib_path)
+    ctpp2_lib = compiler.find_library('ctpp2', dirs:ctpp2_lib_path, required:false)
+    if not ctpp2_lib.found()
+      ctpp2_lib_path = join_paths(ctpp2_prefix_install, 'lib')
+      message(ctpp2_lib_path)
+      ctpp2_lib = compiler.find_library('ctpp2', dirs:ctpp2_lib_path)
+    endif
+    ctpp2_link_args = ['-L'+ctpp2_lib_path, '-lctpp2']
+    if meson.is_cross_build() and host_machine.system() == 'windows'
+      iconv_lib = compiler.find_library('iconv', required:false)
+      if iconv_lib.found()
+        ctpp2_link_args += ['-liconv']
+      endif
+    endif
+    has_ctpp2_dep = true
+    ctpp2_dep = declare_dependency(include_directories:ctpp2_include_dir, link_args:ctpp2_link_args)
+  else
+    message('ctpp2/CTPP2Logger.hpp not found. Compiling without CTPP2 support')
+  endif
+endif
+
+xapian_dep = dependency('xapian-core', required:false, static:static_deps)
+
+all_deps = [thread_dep, libicu_dep, libzim_dep, xapian_dep, pugixml_dep, libcurl_dep]
+if has_ctpp2_dep
+  all_deps += [ctpp2_dep]
+endif
 
 inc = include_directories('include')
 
 conf = configuration_data()
 conf.set('VERSION', '"@0@"'.format(meson.project_version()))
+conf.set('ENABLE_CTPP2', has_ctpp2_dep)
 
 if build_machine.system() == 'windows'
      extra_link_args = ['-lshlwapi', '-lwinmm']
@@ -49,6 +110,16 @@ subdir('src')
 subdir('test')
 
 pkg_requires = ['libzim', 'icu-i18n', 'pugixml', 'libcurl']
+if xapian_dep.found()
+    pkg_requires += ['xapian-core']
+endif
+
+if has_ctpp2_dep
+  extra_libs += ctpp2_link_args
+  if ctpp2_include_path != ''
+    extra_cflags = ' -I'+ctpp2_include_path
+  endif
+endif
 
 pkg_conf = configuration_data()
 pkg_conf.set('prefix', get_option('prefix'))

meson_options.txt

@@ -1,2 +1,4 @@
+option('ctpp2-install-prefix', type : 'string', value : '',
+  description : 'Prefix where ctpp libs has been installed')
 option('android', type : 'boolean', value : false,
   description : 'Do we make a kiwix-lib for android')

scripts/ctpp2c.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+
+ctpp2c=$1
+SOURCE=$(pwd)/$2
+DEST=$3
+
+$ctpp2c $SOURCE $DEST

scripts/kiwix-compile-resources

@@ -81,12 +81,12 @@ class Resource:
             data_identifier="_".join([""]+self.identifier),
             resource_content=",\n    ".join(", ".join("{:#04x}".format(i) for i in r) for r in sliced),
             resource_len=len(self.data),
-            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]),
+            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]), 
             namespaces_close=" ".join(["}"]*(len(self.identifier)-1)),
             identifier=self.identifier[-1],
             env_identifier="RES_"+"_".join(self.identifier)+"_PATH"
         )
-
+    
     def dump_getter(self):
         return resource_getter_template.format(
             common_name=self.filename,
@@ -95,11 +95,11 @@ class Resource:
 
     def dump_decl(self):
         return resource_decl_template.format(
-            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]),
+            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]), 
             namespaces_close=" ".join(["}"]*(len(self.identifier)-1)),
             identifier=self.identifier[-1]
         )
-
+    
 
 
 master_c_template = """//This file is automaically generated. Do not modify it.
@@ -113,7 +113,7 @@ static std::string init_resource(const char* name, const unsigned char* content,
     char * resPath = getenv(name);
     if (NULL == resPath)
         return std::string(reinterpret_cast<const char*>(content), len);
-
+    
     std::ifstream ifs(resPath);
     if (!ifs.good())
         return std::string(reinterpret_cast<const char*>(content), len);
@@ -137,7 +137,7 @@ def gen_c_file(resources, basename):
        include_file=basename,
        basename=to_identifier(basename)
     )
-
+ 
 
 
 master_h_template = """//This file is automaically generated. Do not modify it.

scripts/meson.build

@@ -1,4 +1,5 @@
 
 res_compiler = find_program('kiwix-compile-resources')
+intermediate_ctpp2c = find_program('ctpp2c.sh')
 
 install_data(res_compiler.path(), install_dir:get_option('bindir'))

src/android/kiwix.cpp

@@ -19,7 +19,7 @@
  */
 
 #include <jni.h>
-#include "org_kiwix_kiwixlib_JNIICU.h"
+#include "org_kiwix_kiwixlib_JNIKiwix.h"
 
 #include <iostream>
 #include <string>
@@ -30,8 +30,8 @@
 
 pthread_mutex_t globalLock = PTHREAD_RECURSIVE_MUTEX_INITIALIZER;
 
-JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIICU_setDataDirectory(
-    JNIEnv* env, jclass kclass, jstring dirStr)
+JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwix_setDataDirectory(
+    JNIEnv* env, jobject obj, jstring dirStr)
 {
   std::string cPath = jni2c(dirStr, env);
 

src/android/kiwixlibrary.cpp

@@ -1,72 +0,0 @@
-/*
- * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#include <jni.h>
-#include <android/log.h>
-#include "org_kiwix_kiwixlib_JNIKiwixLibrary.h"
-
-#include "library.h"
-#include "reader.h"
-#include "utils.h"
-
-/* Kiwix Reader JNI functions */
-JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixLibrary_getNativeLibrary(
-    JNIEnv* env, jobject obj)
-{
-  __android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create library");
-  Lock l;
-  try {
-    kiwix::Library* library = new kiwix::Library();
-    return reinterpret_cast<jlong>(new Handle<kiwix::Library>(library));
-  } catch (std::exception& e) {
-    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Error creating ZIM library");
-    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
-    return 0;
-  }
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixLibrary_dispose(JNIEnv* env, jobject obj)
-{
-  Handle<kiwix::Library>::dispose(env, obj);
-}
-
-#define LIBRARY (Handle<kiwix::Library>::getHandle(env, obj))
-
-/* Kiwix library functions */
-JNIEXPORT jboolean JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixLibrary_addBook(JNIEnv* env, jobject obj, jstring path)
-{
-  std::string cPath = jni2c(path, env);
-  bool ret;
-
-  try {
-    kiwix::Reader reader(cPath);
-    kiwix::Book book;
-    book.update(reader);
-    ret = LIBRARY->addBook(book);
-  } catch (std::exception& e) {
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to add the book");
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
-    ret = false;
-  }
-  return ret;
-}

src/android/kiwixreader.cpp

@@ -24,7 +24,7 @@
 #include <android/log.h>
 #include "org_kiwix_kiwixlib_JNIKiwixReader.h"
 
-#include "tools/base64.h"
+#include "common/base64.h"
 #include "reader.h"
 #include "utils.h"
 
@@ -91,7 +91,7 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getId(JNIEnv* env, jobject obj)
 JNIEXPORT jint JNICALL
 Java_org_kiwix_kiwixlib_JNIKiwixReader_getFileSize(JNIEnv* env, jobject obj)
 {
-  jint size = 0;
+  jint size;
 
   try {
     int cSize = READER->getFileSize();
@@ -224,23 +224,8 @@ JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getMimeType(
   return mimeType;
 }
 
-JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_checkUrl(
-     JNIEnv* env, jobject obj, jstring url)
-{
-  jstring finalUrl;
-  std::string cUrl = jni2c(url, env);
-  try {
-    auto entry = READER->getEntryFromEncodedPath(cUrl);
-    entry = entry.getFinalEntry();
-    finalUrl = c2jni(entry.getPath(), env);
-  } catch (std::exception& e) {
-    finalUrl = c2jni("", env);
-  }
-  return finalUrl;
-}
-
 JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContent(
-    JNIEnv* env, jobject obj, jobject url, jobject titleObj, jobject mimeTypeObj, jobject sizeObj)
+    JNIEnv* env, jobject obj, jstring url, jobject titleObj, jobject mimeTypeObj, jobject sizeObj)
 {
   /* Default values */
   setStringObjValue("", titleObj, env);
@@ -249,24 +234,21 @@ JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContent(
   jbyteArray data = env->NewByteArray(0);
 
   /* Retrieve the content */
-  std::string cUrl = getStringObjValue(url, env);
+  std::string cUrl = jni2c(url, env);
   unsigned int cSize = 0;
 
   try {
     auto entry = READER->getEntryFromEncodedPath(cUrl);
-    bool isRedirect = entry.isRedirect();
     entry = entry.getFinalEntry();
     cSize = entry.getSize();
     setIntObjValue(cSize, sizeObj, env);
+
+    data = env->NewByteArray(cSize);
+    env->SetByteArrayRegion(
+        data, 0, cSize, reinterpret_cast<const jbyte*>(entry.getBlob().data()));
+
     setStringObjValue(entry.getMimetype(), mimeTypeObj, env);
     setStringObjValue(entry.getTitle(), titleObj, env);
-    if (isRedirect) {
-      setStringObjValue(entry.getPath(), url, env);
-    } else {
-      data = env->NewByteArray(cSize);
-      env->SetByteArrayRegion(
-          data, 0, cSize, reinterpret_cast<const jbyte*>(entry.getBlob().data()));
-    }
   } catch (std::exception& e) {
     __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get content for url: %s", cUrl.c_str());
     __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
@@ -353,17 +335,14 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_searchSuggestions(JNIEnv* env,
 JNIEXPORT jboolean JNICALL
 Java_org_kiwix_kiwixlib_JNIKiwixReader_getNextSuggestion(JNIEnv* env,
                                                          jobject obj,
-                                                         jobject titleObj,
-                                                         jobject urlObj)
+                                                         jobject titleObj)
 {
   jboolean retVal = JNI_FALSE;
   std::string cTitle;
-  std::string cUrl;
 
   try {
-    if (READER->getNextSuggestion(cTitle, cUrl)) {
+    if (READER->getNextSuggestion(cTitle)) {
       setStringObjValue(cTitle, titleObj, env);
-      setStringObjValue(cUrl, urlObj, env);
       retVal = JNI_TRUE;
     }
   } catch (std::exception& e) {
@@ -427,35 +406,6 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getDescription(JNIEnv* env, jobject obj)
   return description;
 }
 
-JNIEXPORT jint JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixReader_getArticleCount(JNIEnv* env, jobject obj)
-{
-  jint articleCount = 0;
-  try {
-    auto cArticleCount = READER->getArticleCount();
-    articleCount = c2jni(cArticleCount);
-  } catch (std::exception& e) {
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get article count.");
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
-  }
-  return articleCount;
-}
-
-JNIEXPORT jint JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixReader_getMediaCount(JNIEnv* env, jobject obj)
-{
-  jint mediaCount = 0;
-  try {
-    auto cMediaCount = READER->getMediaCount();
-    mediaCount = c2jni(cMediaCount);
-  } catch (std::exception& e) {
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get media count.");
-    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
-  }
-  return mediaCount;
-}
-
-
 JNIEXPORT jboolean JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getRandomPage(
     JNIEnv* env, jobject obj, jobject urlObj)
 {

src/android/kiwixsearcher.cpp

@@ -52,7 +52,7 @@ JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwixSearcher_addReader(
 {
   auto searcher = SEARCHER;
 
-  searcher->add_reader(*(Handle<kiwix::Reader>::getHandle(env, reader)));
+  searcher->add_reader(*(Handle<kiwix::Reader>::getHandle(env, reader)), "");
 }
 
 JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwixSearcher_search(

src/android/kiwixserver.cpp

@@ -1,99 +0,0 @@
-/*
- * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#include <jni.h>
-#include <zim/file.h>
-#include <android/log.h>
-#include "org_kiwix_kiwixlib_JNIKiwixServer.h"
-
-#include "tools/base64.h"
-#include "server.h"
-#include "utils.h"
-
-/* Kiwix Reader JNI functions */
-JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixServer_getNativeServer(
-    JNIEnv* env, jobject obj, jobject jLibrary)
-{
-  __android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create server");
-  Lock l;
-  try {
-    auto library = Handle<kiwix::Library>::getHandle(env, jLibrary);
-    kiwix::Server* server = new kiwix::Server(*library);
-    return reinterpret_cast<jlong>(new Handle<kiwix::Server>(server));
-  } catch (std::exception& e) {
-    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Error creating the server");
-    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
-    return 0;
-  }
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_dispose(JNIEnv* env, jobject obj)
-{
-  Handle<kiwix::Server>::dispose(env, obj);
-}
-
-#define SERVER (Handle<kiwix::Server>::getHandle(env, obj))
-
-/* Kiwix library functions */
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_setRoot(JNIEnv* env, jobject obj, jstring jRoot)
-{
-  std::string root = jni2c(jRoot, env);
-  SERVER->setRoot(root);
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_setAddress(JNIEnv* env, jobject obj, jstring jAddress)
-{
-  std::string address = jni2c(jAddress, env);
-  SERVER->setAddress(address);
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_setPort(JNIEnv* env, jobject obj, int port)
-{
-  SERVER->setPort(port);
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_setNbThreads(JNIEnv* env, jobject obj, int threads)
-{
-  SERVER->setNbThreads(threads);
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_setTaskbar(JNIEnv* env, jobject obj, jboolean withTaskbar, jboolean withLibraryButton)
-{
-  SERVER->setTaskbar(withTaskbar, withLibraryButton);
-}
-
-JNIEXPORT jboolean JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_start(JNIEnv* env, jobject obj)
-{
-  return SERVER->start();
-}
-
-JNIEXPORT void JNICALL
-Java_org_kiwix_kiwixlib_JNIKiwixServer_stop(JNIEnv* env, jobject obj)
-{
-  SERVER->stop();
-}

src/android/meson.build

@@ -1,10 +1,8 @@
 
 kiwix_jni = custom_target('jni',
-  input: ['org/kiwix/kiwixlib/JNIICU.java',
+  input: ['org/kiwix/kiwixlib/JNIKiwix.java',
           'org/kiwix/kiwixlib/JNIKiwixReader.java',
-          'org/kiwix/kiwixlib/JNIKiwixLibrary.java',
           'org/kiwix/kiwixlib/JNIKiwixSearcher.java',
-          'org/kiwix/kiwixlib/JNIKiwixServer.java',
           'org/kiwix/kiwixlib/JNIKiwixInt.java',
           'org/kiwix/kiwixlib/JNIKiwixString.java',
           'org/kiwix/kiwixlib/JNIKiwixBool.java',
@@ -12,19 +10,15 @@ kiwix_jni = custom_target('jni',
           'org/kiwix/kiwixlib/Pair.java'],
   output: ['org_kiwix_kiwixlib_JNIKiwix.h',
            'org_kiwix_kiwixlib_JNIKiwixReader.h',
-           'org_kiwix_kiwixlib_JNIKiwixLibrary.h',
-           'org_kiwix_kiwixlib_JNIKiwixServer.h',
            'org_kiwix_kiwixlib_JNIKiwixSearcher.h',
            'org_kiwix_kiwixlib_JNIKiwixSearcher_Result.h'],
   command:['javac', '-d', '@OUTDIR@', '-h', '@OUTDIR@', '@INPUT@']
 )
 
 kiwix_sources += [
-    'android/kiwixicu.cpp',
+    'android/kiwix.cpp',
     'android/kiwixreader.cpp',
-    'android/kiwixlibrary.cpp',
     'android/kiwixsearcher.cpp',
-    'android/kiwixserver.cpp',
     kiwix_jni]
 
 install_subdir('org', install_dir: 'kiwix-lib/java')

src/android/org/kiwix/kiwixlib/JNIICU.java

@@ -1,26 +0,0 @@
-/*
- * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-package org.kiwix.kiwixlib;
-
-public class JNIICU
-{
-  static public native void setDataDirectory(String icuDataDir);
-}

src/android/org/kiwix/kiwixlib/JNIKiwix.java

@@ -20,17 +20,12 @@
 
 package org.kiwix.kiwixlib;
 
-import android.content.Context;
-import com.getkeepsafe.relinker.ReLinker;
-import org.kiwix.kiwixlib.JNIICU;
+import org.kiwix.kiwixlib.JNIKiwixReader;
+import org.kiwix.kiwixlib.JNIKiwixString;
 
 public class JNIKiwix
 {
-  public JNIKiwix(final Context context){
-    ReLinker.loadLibrary(context, "kiwix");
-  }
+  static { System.loadLibrary("kiwix"); }
 
-  public void setDataDirectory(String icuDataDir) {
-    JNIICU.setDataDirectory(icuDataDir);
-  }
+  public native void setDataDirectory(String icuDataDir);
 }

src/android/org/kiwix/kiwixlib/JNIKiwixLibrary.java

@@ -1,38 +0,0 @@
-/*
- * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-package org.kiwix.kiwixlib;
-
-import org.kiwix.kiwixlib.JNIKiwixException;
-
-public class JNIKiwixLibrary
-{
-  public native boolean addBook(String path) throws JNIKiwixException;
-
-  public JNIKiwixLibrary()
-  {
-    nativeHandle = getNativeLibrary();
-  }
-
-  public native void dispose();
-
-  private native long getNativeLibrary();
-  private long nativeHandle;
-}

src/android/org/kiwix/kiwixlib/JNIKiwixReader.java

@@ -38,31 +38,7 @@ public class JNIKiwixReader
 
   public native String getMimeType(String url);
 
-  /**
-   * Check if a url exists and is a redirect or not.
-   *
-   * Return an empty string if the url doesn't exist in the reader.
-   * Return the url of the "final" entry.
-   * - equal to the input url if the entry is not a redirection.
-   * - different if the url is a redirection (and the webview should redirect to it).
-   */
-  public native String checkUrl(String url);
-
-  /**
-   * Get the content of a article.
-   *
-   * Return a byte array of the content of the article.
-   * Set the title, mimeType to the title and mimeType of the article.
-   * Set the size to the size of the returned array.
-   *
-   * If the entry doesn't exist :
-   *  - return a empty byte array
-   *  - set all arguments (except url) to empty/0.
-   * If the entry exist but is a redirection :
-   *  - return an empty byte array
-   *  - set all arguments (including url) to information of the targeted article.
-   */
-  public native byte[] getContent(JNIKiwixString url,
+  public native byte[] getContent(String url,
                                   JNIKiwixString title,
                                   JNIKiwixString mimeType,
                                   JNIKiwixInt size);
@@ -102,7 +78,7 @@ public class JNIKiwixReader
 
   public native boolean searchSuggestions(String prefix, int count);
 
-  public native boolean getNextSuggestion(JNIKiwixString title, JNIKiwixString url);
+  public native boolean getNextSuggestion(JNIKiwixString title);
 
   public native boolean getPageUrlFromTitle(String title, JNIKiwixString url);
 

src/android/org/kiwix/kiwixlib/JNIKiwixServer.java

@@ -1,48 +0,0 @@
-/*
- * Copyright (C) 2019 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-package org.kiwix.kiwixlib;
-
-import org.kiwix.kiwixlib.JNIKiwixException;
-import org.kiwix.kiwixlib.JNIKiwixLibrary;
-
-public class JNIKiwixServer
-{
-  public native void setRoot(String root);
-
-  public native void setAddress(String address);
-
-  public native void setPort(int port);
-
-  public native void setNbThreads(int nbTreads);
-
-  public native void setTaskbar(boolean withTaskBar, boolean witLibraryButton);
-
-  public native boolean start();
-
-  public native void stop();
-
-  public JNIKiwixServer(JNIKiwixLibrary library)
-  {
-    nativeHandle = getNativeServer(library);
-  }
-
-  private native long getNativeServer(JNIKiwixLibrary library);
-  private long nativeHandle;
-}

src/android/org/kiwix/kiwixlib/JNIKiwixString.java

@@ -22,16 +22,4 @@ package org.kiwix.kiwixlib;
 public class JNIKiwixString
 {
   public String value;
-
-  public JNIKiwixString(String value) {
-    this.value = value;
-  }
-
-  public JNIKiwixString() {
-    this("");
-  }
-
-  public String getValue() {
-    return value;
-  }
 }

src/android/utils.h

@@ -114,13 +114,6 @@ inline std::string jni2c(const jstring& val, JNIEnv* env)
 
 inline int jni2c(const jint val) { return (int)val; }
 /* Method to deal with variable passed by reference */
-inline std::string getStringObjValue(const jobject obj, JNIEnv* env)
-{
-  jclass objClass = env->GetObjectClass(obj);
-  jfieldID objFid = env->GetFieldID(objClass, "value", "Ljava/lang/String;");
-  jstring jstr = (jstring)env->GetObjectField(obj, objFid);
-  return jni2c(jstr, env);
-}
 inline void setStringObjValue(const std::string& value,
                               const jobject obj,
                               JNIEnv* env)

src/aria2.cpp

@@ -2,24 +2,13 @@
 
 #include "aria2.h"
 #include "xmlrpc.h"
-#include <iostream>
 #include <sstream>
 #include <thread>
 #include <chrono>
-#include <tools/otherTools.h>
-#include <tools/pathTools.h>
-#include <tools/stringTools.h>
+#include <common/otherTools.h>
+#include <common/pathTools.h>
 #include <downloader.h> // For AriaError
 
-#ifdef _WIN32
-# define ARIA2_CMD "aria2c.exe"
-#else
-# define ARIA2_CMD "aria2c"
-# include <unistd.h>
-#endif
-
-
-
 namespace kiwix {
 
 Aria2::Aria2():
@@ -30,7 +19,6 @@ Aria2::Aria2():
   m_lock(PTHREAD_MUTEX_INITIALIZER)
 {
   m_downloadDir = getDataDirectory();
-  makeDirectory(m_downloadDir);
   std::vector<const char*> callCmd;
 
   std::string rpc_port = "--rpc-listen-port=" + to_string(m_port);
@@ -48,16 +36,11 @@ Aria2::Aria2():
   std::string rpc_secret = "--rpc-secret=" + m_secret;
   m_secret = "token:"+m_secret;
 
-  std::string aria2cmd = appendToDirectory(
-    removeLastPathElement(getExecutablePath(true)),
-    ARIA2_CMD);
-  if (fileExists(aria2cmd)) {
-    // A local aria2c exe exists (packaged with kiwix-desktop), use it.
-    callCmd.push_back(aria2cmd.c_str());
-  } else {
-    // Try to use a potential installed aria2c.
-    callCmd.push_back(ARIA2_CMD);
-  }
+#ifdef _WIN32
+  callCmd.push_back("aria2c.exe");
+#else
+  callCmd.push_back("aria2c");
+#endif
   callCmd.push_back("--enable-rpc");
   callCmd.push_back(rpc_secret.c_str());
   callCmd.push_back(rpc_port.c_str());
@@ -78,32 +61,18 @@ Aria2::Aria2():
   callCmd.push_back("--max-concurrent-downloads=42");
   callCmd.push_back("--rpc-max-request-size=6M");
   callCmd.push_back("--file-allocation=none");
-  for (auto &cmd : callCmd) {
-      m_launchCmd.append(cmd).append(" ");
-  }
   mp_aria = Subprocess::run(callCmd);
   mp_curl = curl_easy_init();
-  char errbuf[CURL_ERROR_SIZE];
   curl_easy_setopt(mp_curl, CURLOPT_URL, "http://localhost/rpc");
   curl_easy_setopt(mp_curl, CURLOPT_PORT, m_port);
   curl_easy_setopt(mp_curl, CURLOPT_POST, 1L);
-  curl_easy_setopt(mp_curl, CURLOPT_ERRORBUFFER, errbuf);
 
   int watchdog = 50;
   while(--watchdog) {
-    sleep(10);
-    errbuf[0] = 0;
+    std::this_thread::sleep_for(std::chrono::microseconds(100));
     auto res = curl_easy_perform(mp_curl);
     if (res == CURLE_OK) {
       break;
-    } else if (watchdog == 1) {
-      std::cerr <<" curl_easy_perform() failed." << std::endl;
-      fprintf(stderr, "\nlibcurl: (%d) ", res);
-      if (errbuf[0] != 0) {
-        std::cerr << errbuf << std::endl;
-      } else {
-        std::cerr << curl_easy_strerror(res) << std::endl;
-      }
     }
   }
   if (!watchdog) {
@@ -189,6 +158,7 @@ std::vector<std::string> Aria2::tellActive()
   MethodCall methodCall("aria2.tellActive", m_secret);
   auto statusArray = methodCall.newParamValue().getArray();
   statusArray.addValue().set(std::string("gid"));
+  statusArray.addValue().set(std::string("following"));
   auto responseContent = doRequest(methodCall);
   MethodResponse response(responseContent);
   std::vector<std::string> activeGID;
@@ -203,27 +173,6 @@ std::vector<std::string> Aria2::tellActive()
   return activeGID;
 }
 
-std::vector<std::string> Aria2::tellWaiting()
-{
-  MethodCall methodCall("aria2.tellWaiting", m_secret);
-  methodCall.newParamValue().set(0);
-  methodCall.newParamValue().set(99); // max number of downloads to be returned, don't know how to set this properly assumed that there will not be more than 99 paused downloads.
-  auto statusArray = methodCall.newParamValue().getArray();
-  statusArray.addValue().set(std::string("gid"));
-  auto responseContent = doRequest(methodCall);
-  MethodResponse response(responseContent);
-  std::vector<std::string> waitingGID;
-  int index = 0;
-  while(true) {
-    try {
-      auto structNode = response.getParamValue(0).getArray().getValue(index++).getStruct();
-      auto gidNode = structNode.getMember("gid");
-      waitingGID.push_back(gidNode.getValue().getAsS());
-    } catch (InvalidRPCNode& e) { break; }
-  }
-  return waitingGID;
-}
-
 void Aria2::saveSession()
 {
   MethodCall methodCall("aria2.saveSession", m_secret);
@@ -237,25 +186,5 @@ void Aria2::shutdown()
   doRequest(methodCall);
 }
 
-void Aria2::pause(const std::string& gid)
-{
-    MethodCall methodCall("aria2.pause", m_secret);
-    methodCall.newParamValue().set(gid);
-    doRequest(methodCall);
-}
-
-void Aria2::unpause(const std::string& gid)
-{
-    MethodCall methodCall("aria2.unpause", m_secret);
-    methodCall.newParamValue().set(gid);
-    doRequest(methodCall);
-}
-
-void Aria2::remove(const std::string& gid)
-{
-    MethodCall methodCall("aria2.remove", m_secret);
-    methodCall.newParamValue().set(gid);
-    doRequest(methodCall);
-}
 
 } // end namespace kiwix

src/aria2.h

@@ -26,7 +26,6 @@ class Aria2
     std::string m_downloadDir;
     CURL* mp_curl;
     pthread_mutex_t m_lock;
-    std::string m_launchCmd;
 
     std::string doRequest(const MethodCall& methodCall);
 
@@ -38,13 +37,8 @@ class Aria2
     std::string addUri(const std::vector<std::string>& uri);
     std::string tellStatus(const std::string& gid, const std::vector<std::string>& statusKey);
     std::vector<std::string> tellActive();
-    std::vector<std::string> tellWaiting();
     void saveSession();
     void shutdown();
-    void pause(const std::string& gid);
-    void unpause(const std::string& gid);
-    void remove(const std::string& gid);
-    const std::string &getLaunchCmd() { return m_launchCmd; };
 };
 
 }; //end namespace kiwix

src/book.cpp

@@ -20,18 +20,16 @@
 #include "book.h"
 #include "reader.h"
 
-#include "tools/base64.h"
-#include "tools/regexTools.h"
-#include "tools/networkTools.h"
+#include "common/base64.h"
+#include "common/regexTools.h"
+#include "common/networkTools.h"
 
 #include <pugixml.hpp>
 
 namespace kiwix
 {
 /* Constructor */
-Book::Book() :
-  m_pathValid(false),
-  m_readOnly(false)
+Book::Book() : m_readOnly(false)
 {
 }
 /* Destructor */
@@ -48,7 +46,6 @@ bool Book::update(const kiwix::Book& other)
 
   if (m_path.empty()) {
     m_path = other.m_path;
-    m_pathValid = other.m_pathValid;
   }
 
   if (m_url.empty()) {
@@ -63,6 +60,11 @@ bool Book::update(const kiwix::Book& other)
     m_name = other.m_name;
   }
 
+  if (m_indexPath.empty()) {
+    m_indexPath = other.m_indexPath;
+    m_indexType = other.m_indexType;
+  }
+
   if (m_faviconMimeType.empty()) {
     m_favicon = other.m_favicon;
     m_faviconMimeType = other.m_faviconMimeType;
@@ -86,7 +88,6 @@ void Book::update(const kiwix::Reader& reader)
   m_articleCount = reader.getArticleCount();
   m_mediaCount = reader.getMediaCount();
   m_size = static_cast<uint64_t>(reader.getFileSize()) << 10;
-  m_pathValid = true;
 
   reader.getFavicon(m_favicon, m_faviconMimeType);
 }
@@ -100,6 +101,14 @@ void Book::updateFromXml(const pugi::xml_node& node, const std::string& baseDir)
     path = computeAbsolutePath(baseDir, path);
   }
   m_path = path;
+  path = ATTR("indexPath");
+  if (!path.empty()) {
+    if (isRelativePath(path)) {
+      path = computeAbsolutePath(baseDir, path);
+    }
+    m_indexPath = path;
+    m_indexType = XAPIAN;
+  }
   m_title = ATTR("title");
   m_name = ATTR("name");
   m_tags = ATTR("tags");
@@ -122,14 +131,6 @@ void Book::updateFromXml(const pugi::xml_node& node, const std::string& baseDir)
 #undef ATTR
 
 
-static std::string fromOpdsDate(const std::string& date)
-{
-  //The opds date use the standard <YYYY>-<MM>-<DD>T<HH>:<mm>:<SS>Z
-  //and we want <YYYY>-<MM>-<DD>. That's easy, let's take the first 10 char
-  return date.substr(0, 10);
-}
-
-
 #define VALUE(name) node.child(name).child_value()
 void Book::updateFromOpds(const pugi::xml_node& node, const std::string& urlHost)
 {
@@ -140,9 +141,8 @@ void Book::updateFromOpds(const pugi::xml_node& node, const std::string& urlHost
   m_title = VALUE("title");
   m_description = VALUE("description");
   m_language = VALUE("language");
-  m_date = fromOpdsDate(VALUE("updated"));
+  m_date = VALUE("updated");
   m_creator = node.child("author").child("name").child_value();
-  m_tags = VALUE("tags");
   for(auto linkNode = node.child("link"); linkNode;
            linkNode = linkNode.next_sibling("link")) {
     std::string rel = linkNode.attribute("rel").value();
@@ -160,7 +160,7 @@ void Book::updateFromOpds(const pugi::xml_node& node, const std::string& urlHost
 }
 #undef VALUE
 
-std::string Book::getHumanReadableIdFromPath() const
+std::string Book::getHumanReadableIdFromPath()
 {
   std::string id = m_path;
   if (!id.empty()) {
@@ -186,6 +186,13 @@ void Book::setPath(const std::string& path)
    : path;
 }
 
+void Book::setIndexPath(const std::string& indexPath)
+{
+  m_indexPath = isRelativePath(indexPath)
+    ? computeAbsolutePath(getCurrentDirectory(), indexPath)
+    : indexPath;
+}
+
 const std::string& Book::getFavicon() const {
   if (m_favicon.empty() && !m_faviconUrl.empty()) {
     try {

src/bookmark.cpp

@@ -1,47 +0,0 @@
-/*
- * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "bookmark.h"
-
-#include <pugixml.hpp>
-
-namespace kiwix
-{
-/* Constructor */
-Bookmark::Bookmark()
-{
-}
-
-/* Destructor */
-Bookmark::~Bookmark()
-{
-}
-
-void Bookmark::updateFromXml(const pugi::xml_node& node)
-{
-  auto bookNode = node.child("book");
-  m_bookId = bookNode.child("id").child_value();
-  m_bookTitle = bookNode.child("title").child_value();
-  m_language = bookNode.child("language").child_value();
-  m_date = bookNode.child("date").child_value();
-  m_title = node.child("title").child_value();
-  m_url = node.child("url").child_value();
-}
-
-}

src/common/base64.cpp

@@ -1,4 +1,4 @@
-/*
+/* 
    base64.cpp and base64.h
 
    Copyright (C) 2004-2008 René Nyffenegger
@@ -24,10 +24,10 @@
    René Nyffenegger rene.nyffenegger@adp-gmbh.ch
 */
 
-#include <tools/base64.h>
+#include <common/base64.h>
 #include <iostream>
 
-static const std::string base64_chars =
+static const std::string base64_chars = 
              "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
              "abcdefghijklmnopqrstuvwxyz"
   "0123456789+/";

src/common/networkTools.cpp

@@ -0,0 +1,209 @@
+/*
+ * Copyright 2012 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <common/networkTools.h>
+
+#ifdef _WIN32
+#include <winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <net/if.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+#endif
+
+#include <curl/curl.h>
+
+#include <sstream>
+#include <iostream>
+
+
+std::map<std::string, std::string> kiwix::getNetworkInterfaces()
+{
+  std::map<std::string, std::string> interfaces;
+
+#ifdef _WIN32
+  SOCKET sd = WSASocket(AF_INET, SOCK_DGRAM, 0, 0, 0, 0);
+  if (sd == (SOCKET)SOCKET_ERROR) {
+    std::cerr << "Failed to get a socket. Error " << WSAGetLastError()
+              << std::endl;
+    return interfaces;
+  }
+
+  INTERFACE_INFO InterfaceList[20];
+  unsigned long nBytesReturned;
+  if (WSAIoctl(sd,
+               SIO_GET_INTERFACE_LIST,
+               0,
+               0,
+               &InterfaceList,
+               sizeof(InterfaceList),
+               &nBytesReturned,
+               0,
+               0)
+      == SOCKET_ERROR) {
+    std::cerr << "Failed calling WSAIoctl: error " << WSAGetLastError()
+              << std::endl;
+    return interfaces;
+  }
+
+  int nNumInterfaces = nBytesReturned / sizeof(INTERFACE_INFO);
+  for (int i = 0; i < nNumInterfaces; ++i) {
+    sockaddr_in* pAddress;
+    pAddress = (sockaddr_in*)&(InterfaceList[i].iiAddress);
+
+    /* Add to the map */
+    std::string interfaceName = std::string(inet_ntoa(pAddress->sin_addr));
+    std::string interfaceIp = std::string(inet_ntoa(pAddress->sin_addr));
+    interfaces.insert(
+        std::pair<std::string, std::string>(interfaceName, interfaceIp));
+  }
+#else
+  /* Get Network interfaces information */
+  char buf[16384];
+  struct ifconf ifconf;
+  int fd = socket(PF_INET, SOCK_DGRAM, 0); /* Only IPV4 */
+  ifconf.ifc_len = sizeof buf;
+  ifconf.ifc_buf = buf;
+  if (ioctl(fd, SIOCGIFCONF, &ifconf) != 0) {
+    perror("ioctl(SIOCGIFCONF)");
+    exit(EXIT_FAILURE);
+  }
+
+  /* Go through each interface */
+  int i;
+  size_t len;
+  struct ifreq* ifreq;
+  ifreq = ifconf.ifc_req;
+  for (i = 0; i < ifconf.ifc_len;) {
+    if (ifreq->ifr_addr.sa_family == AF_INET) {
+      /* Get the network interface ip */
+      char host[128] = {0};
+      const int error = getnameinfo(&(ifreq->ifr_addr),
+                                    sizeof ifreq->ifr_addr,
+                                    host,
+                                    sizeof host,
+                                    0,
+                                    0,
+                                    NI_NUMERICHOST);
+      if (!error) {
+        std::string interfaceName = std::string(ifreq->ifr_name);
+        std::string interfaceIp = std::string(host);
+        /* Add to the map */
+        interfaces.insert(
+            std::pair<std::string, std::string>(interfaceName, interfaceIp));
+      } else {
+        perror("getnameinfo()");
+      }
+    }
+
+/* some systems have ifr_addr.sa_len and adjust the length that
+ * way, but not mine. weird */
+#ifndef __linux__
+    len = IFNAMSIZ + ifreq->ifr_addr.sa_len;
+#else
+    len = sizeof *ifreq;
+#endif
+    ifreq = (struct ifreq*)((char*)ifreq + len);
+    i += len;
+  }
+#endif
+  return interfaces;
+}
+
+std::string kiwix::getBestPublicIp()
+{
+  std::map<std::string, std::string> interfaces = kiwix::getNetworkInterfaces();
+
+#ifndef _WIN32
+  const char* const prioritizedNames[]
+      = {"eth0", "eth1", "wlan0", "wlan1", "en0", "en1"};
+  const int count = (sizeof prioritizedNames) / (sizeof prioritizedNames[0]);
+  for (int i = 0; i < count; ++i) {
+    std::map<std::string, std::string>::const_iterator it
+        = interfaces.find(prioritizedNames[i]);
+    if (it != interfaces.end()) {
+      return it->second;
+    }
+  }
+#endif
+
+  for (std::map<std::string, std::string>::iterator iter = interfaces.begin();
+       iter != interfaces.end();
+       ++iter) {
+    std::string interfaceIp = iter->second;
+    if (interfaceIp.length() >= 7 && interfaceIp.substr(0, 7) == "192.168") {
+      return interfaceIp;
+    }
+  }
+
+  for (std::map<std::string, std::string>::iterator iter = interfaces.begin();
+       iter != interfaces.end();
+       ++iter) {
+    std::string interfaceIp = iter->second;
+    if (interfaceIp.length() >= 7 && interfaceIp.substr(0, 7) == "172.16.") {
+      return interfaceIp;
+    }
+  }
+
+  for (std::map<std::string, std::string>::iterator iter = interfaces.begin();
+       iter != interfaces.end();
+       ++iter) {
+    std::string interfaceIp = iter->second;
+    if (interfaceIp.length() >= 3 && interfaceIp.substr(0, 3) == "10.") {
+      return interfaceIp;
+    }
+  }
+
+  return "127.0.0.1";
+}
+
+size_t write_callback_to_iss(char* ptr, size_t size, size_t nmemb, void* userdata)
+{
+  auto str = static_cast<std::stringstream*>(userdata);
+  str->write(ptr, nmemb);
+  return nmemb;
+}
+
+std::string kiwix::download(const std::string& url) {
+  auto curl = curl_easy_init();
+  std::stringstream ss;
+  curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
+  curl_easy_setopt(curl, CURLOPT_HTTPGET, 1L);
+  curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, &write_callback_to_iss);
+  curl_easy_setopt(curl, CURLOPT_WRITEDATA, &ss);
+  auto res = curl_easy_perform(curl);
+  if (res != CURLE_OK) {
+    curl_easy_cleanup(curl);
+    throw std::runtime_error("Cannot perform request");
+  }
+  long response_code;
+  curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &response_code);
+  curl_easy_cleanup(curl);
+  if (response_code != 200) {
+    throw std::runtime_error("Invalid return code from server");
+  }
+  return ss.str();
+}

src/common/otherTools.cpp

@@ -0,0 +1,326 @@
+/*
+ * Copyright 2014 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <common/otherTools.h>
+#include <map>
+
+static std::map<std::string, std::string> codeisomapping {
+//a
+  { "ad", "and" },
+  { "ae", "are" },
+  { "af", "afg" },
+  { "ag", "atg" },
+  { "ai", "aia" },
+  { "al", "alb" },
+  { "am", "arm" },
+  { "an", "ant" },
+  { "ao", "ago" },
+  { "aq", "ata" },
+  { "ar", "arg" },
+  { "as", "asm" },
+  { "at", "aut" },
+  { "au", "aus" },
+  { "aw", "abw" },
+  { "ax", "ala" },
+  { "az", "aze" },
+//b
+  { "ba", "bih" },
+  { "bb", "brb" },
+  { "bd", "bgd" },
+  { "be", "bel" },
+  { "bf", "bfa" },
+  { "bg", "bgr" },
+  { "bh", "bhr" },
+  { "bi", "bdi" },
+  { "bj", "ben" },
+  { "bl", "blm" },
+  { "bn", "brn" },
+  { "bm", "bmu" },
+  { "bo", "bol" },
+  { "br", "bra" },
+  { "bs", "bhs" },
+  { "bt", "btn" },
+  { "bv", "bvt" },
+  { "bw", "bwa" },
+  { "by", "blr" },
+  { "bz", "blz" },
+//c
+  { "ca", "can" },
+  { "cc", "cck" },
+  { "cd", "cod" },
+  { "cf", "caf" },
+  { "cg", "cog" },
+  { "ch", "che" },
+  { "ci", "civ" },
+  { "ck", "cok" },
+  { "cl", "chl" },
+  { "cm", "cmr" },
+  { "cn", "chn" },
+  { "co", "col" },
+  { "cr", "cri" },
+  { "cu", "cub" },
+  { "cv", "cpv" },
+  { "cx", "cxr" },
+  { "cy", "cyp" },
+  { "cz", "cze" },
+//d
+  { "de", "deu" },
+  { "dj", "dji" },
+  { "dk", "dnk" },
+  { "dm", "dma" },
+  { "do", "dom" },
+  { "dz", "dza" },
+//e
+  { "ec", "ecu" },
+  { "ee", "est" },
+  { "eg", "egy" },
+  { "eh", "esh" },
+  { "en", "eng" },
+  { "er", "eri" },
+  { "es", "esp" },
+  { "et", "eth" },
+//f
+  { "fi", "fin" },
+  { "fj", "fji" },
+  { "fk", "flk" },
+  { "fm", "fsm" },
+  { "fo", "fro" },
+  { "fr", "fra" },
+//g
+  { "ga", "gab" },
+  { "gb", "gbr" },
+  { "gd", "grd" },
+  { "ge", "geo" },
+  { "gf", "guf" },
+  { "gg", "ggy" },
+  { "gh", "gha" },
+  { "gi", "gib" },
+  { "gl", "grl" },
+  { "gm", "gmb" },
+  { "gn", "gin" },
+  { "gp", "glp" },
+  { "gq", "gnq" },
+  { "gr", "grc" },
+  { "gs", "sgs" },
+  { "gt", "gtm" },
+  { "gu", "gum" },
+  { "gw", "gnb" },
+  { "gy", "guy" },
+//h
+  { "hk", "hkg" },
+  { "hm", "hmd" },
+  { "hn", "hnd" },
+  { "hr", "hrv" },
+  { "ht", "hti" },
+  { "hu", "hun" },
+//i
+  { "id", "idn" },
+  { "ie", "irl" },
+  { "il", "isr" },
+  { "im", "imn" },
+  { "in", "ind" },
+  { "io", "iot" },
+  { "iq", "irq" },
+  { "ir", "irn" },
+  { "is", "isl" },
+  { "it", "ita" },
+//j
+  { "je", "jey" },
+  { "jm", "jam" },
+  { "jo", "jor" },
+  { "jp", "jpn" },
+//k
+  { "ke", "ken" },
+  { "kg", "kgz" },
+  { "kh", "khm" },
+  { "ki", "kir" },
+  { "km", "com" },
+  { "kn", "kna" },
+  { "kp", "prk" },
+  { "kr", "kor" },
+  { "kw", "kwt" },
+  { "ky", "cym" },
+  { "kz", "kaz" },
+//l
+  { "la", "lao" },
+  { "lb", "lbn" },
+  { "lc", "lca" },
+  { "li", "lie" },
+  { "lk", "lka" },
+  { "lr", "lbr" },
+  { "ls", "lso" },
+  { "lt", "ltu" },
+  { "lu", "lux" },
+  { "lv", "lva" },
+  { "ly", "lby" },
+//m
+  { "ma", "mar" },
+  { "mc", "mco" },
+  { "md", "mda" },
+  { "me", "mne" },
+  { "mf", "maf" },
+  { "mg", "mdg" },
+  { "mh", "mhl" },
+  { "mk", "mkd" },
+  { "ml", "mli" },
+  { "mm", "mmr" },
+  { "mn", "mng" },
+  { "mo", "mac" },
+  { "mp", "mnp" },
+  { "mq", "mtq" },
+  { "mr", "mrt" },
+  { "ms", "msr" },
+  { "mt", "mlt" },
+  { "mu", "mus" },
+  { "mv", "mdv" },
+  { "mw", "mwi" },
+  { "mx", "mex" },
+  { "my", "mys" },
+  { "mz", "moz" },
+//n
+  { "na", "nam" },
+  { "nc", "ncl" },
+  { "ne", "ner" },
+  { "nf", "nfk" },
+  { "ng", "nga" },
+  { "ni", "nic" },
+  { "nl", "nld" },
+  { "no", "nor" },
+  { "np", "npl" },
+  { "nr", "nru" },
+  { "nu", "niu" },
+  { "nz", "nzl" },
+//o
+  { "om", "omn" },
+//p
+  { "pa", "pan" },
+  { "pe", "per" },
+  { "pf", "pyf" },
+  { "pg", "png" },
+  { "ph", "phl" },
+  { "pk", "pak" },
+  { "pl", "pol" },
+  { "pm", "spm" },
+  { "pn", "pcn" },
+  { "pr", "pri" },
+  { "ps", "pse" },
+  { "pt", "prt" },
+  { "pw", "plw" },
+  { "py", "pry" },
+//q
+  { "qa", "qat" },
+//r
+  { "re", "reu" },
+  { "ro", "rou" },
+  { "rs", "srb" },
+  { "ru", "rus" },
+  { "rw", "rwa" },
+//s
+  { "sa", "sau" },
+  { "sb", "slb" },
+  { "sc", "syc" },
+  { "sd", "sdn" },
+  { "se", "swe" },
+  { "sg", "sgp" },
+  { "sh", "shn" },
+  { "si", "svn" },
+  { "sj", "sjm" },
+  { "sk", "svk" },
+  { "sl", "sle" },
+  { "sm", "smr" },
+  { "sn", "sen" },
+  { "so", "som" },
+  { "sr", "sur" },
+  { "ss", "ssd" },
+  { "st", "stp" },
+  { "sv", "slv" },
+  { "sy", "syr" },
+  { "sz", "swz" },
+//t
+  { "tc", "tca" },
+  { "td", "tcd" },
+  { "tf", "atf" },
+  { "tg", "tgo" },
+  { "th", "tha" },
+  { "tj", "tjk" },
+  { "tk", "tkl" },
+  { "tl", "tls" },
+  { "tm", "tkm" },
+  { "tn", "tun" },
+  { "to", "ton" },
+  { "tr", "tur" },
+  { "tt", "tto" },
+  { "tv", "tuv" },
+  { "tw", "twn" },
+  { "tz", "tza" },
+//u
+  { "ua", "ukr" },
+  { "ug", "uga" },
+  { "um", "umi" },
+  { "us", "usa" },
+  { "uy", "ury" },
+  { "uz", "uzb" },
+//v
+  { "va", "vat" },
+  { "vc", "vct" },
+  { "ve", "ven" },
+  { "vg", "vgb" },
+  { "vi", "vir" },
+  { "vn", "vnm" },
+  { "vu", "vut" },
+//w
+  { "wf", "wlf" },
+  { "ws", "wsm" },
+//y
+  { "ye", "yem" },
+  { "yt", "myt" },
+// z
+  { "za", "zaf" },
+  { "zm", "zmb" },
+  { "zw", "zwe" }
+};
+
+void kiwix::sleep(unsigned int milliseconds)
+{
+#ifdef _WIN32
+  Sleep(milliseconds);
+#else
+  usleep(1000 * milliseconds);
+#endif
+}
+
+
+struct XmlStringWriter: pugi::xml_writer
+{
+  std::string result;
+  virtual void write(const void* data, size_t size){
+    result.append(static_cast<const char*>(data), size);
+  }
+};
+
+std::string kiwix::nodeToString(pugi::xml_node node)
+{
+  XmlStringWriter writer;
+  node.print(writer, "  ");
+  return writer.result;
+}
+
+std::string kiwix::converta2toa3(const std::string& a2code){
+  return codeisomapping.at(a2code);
+}

src/common/pathTools.cpp

@@ -0,0 +1,335 @@
+/*
+ * Copyright 2011-2014 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <common/pathTools.h>
+
+#ifdef __APPLE__
+#include <limits.h>
+#include <mach-o/dyld.h>
+#elif _WIN32
+#include <direct.h>
+#include <windows.h>
+#include "shlwapi.h"
+#define getcwd _getcwd  // stupid MSFT "deprecation" warning
+#endif
+
+#ifdef _WIN32
+#else
+#include <unistd.h>
+#endif
+
+#ifdef _WIN32
+const std::string SEPARATOR("\\");
+#else
+const std::string SEPARATOR("/");
+#include <unistd.h>
+#endif
+
+#include <stdlib.h>
+
+#ifndef PATH_MAX
+#define PATH_MAX 1024
+#endif
+
+bool isRelativePath(const string& path)
+{
+#ifdef _WIN32
+  return path.empty() || path.substr(1, 2) == ":\\" ? false : true;
+#else
+  return path.empty() || path.substr(0, 1) == "/" ? false : true;
+#endif
+}
+
+string computeRelativePath(const string path, const string absolutePath)
+{
+  std::vector<std::string> pathParts = kiwix::split(path, SEPARATOR);
+  std::vector<std::string> absolutePathParts
+      = kiwix::split(absolutePath, SEPARATOR);
+
+  unsigned int commonCount = 0;
+  while (commonCount < pathParts.size()
+         && commonCount < absolutePathParts.size()
+         && pathParts[commonCount] == absolutePathParts[commonCount]) {
+      commonCount++;
+  }
+
+  string relativePath;
+#ifdef _WIN32
+  /* On Windows you have a token more because the root is represented
+     by a letter */
+  if (commonCount == 0) {
+    relativePath = ".." + SEPARATOR;
+  }
+#endif
+
+  for (unsigned int i = commonCount; i < pathParts.size(); i++) {
+    relativePath += ".." + SEPARATOR;
+  }
+  for (unsigned int i = commonCount; i < absolutePathParts.size(); i++) {
+    relativePath += absolutePathParts[i];
+    relativePath += i + 1 < absolutePathParts.size() ? SEPARATOR : "";
+  }
+  return relativePath;
+}
+
+/* Warning: the relative path must be with slashes */
+string computeAbsolutePath(const string path, const string relativePath)
+{
+  string absolutePath;
+
+  if (path.empty()) {
+    char* path = NULL;
+    size_t size = 0;
+
+#ifdef _WIN32
+    path = _getcwd(path, size);
+#else
+    path = getcwd(path, size);
+#endif
+
+    absolutePath = string(path) + SEPARATOR;
+  } else {
+    absolutePath = path.substr(path.length() - 1, 1) == SEPARATOR
+                       ? path
+                       : path + SEPARATOR;
+  }
+
+#if _WIN32
+  char* cRelativePath = _strdup(relativePath.c_str());
+#else
+  char* cRelativePath = strdup(relativePath.c_str());
+#endif
+  char* token = strtok(cRelativePath, "/");
+
+  while (token != NULL) {
+    if (string(token) == "..") {
+      absolutePath = removeLastPathElement(absolutePath, true, false);
+      token = strtok(NULL, "/");
+    } else if (strcmp(token, ".") && strcmp(token, "")) {
+      absolutePath += string(token);
+      token = strtok(NULL, "/");
+      if (token != NULL) {
+        absolutePath += SEPARATOR;
+      }
+    } else {
+      token = strtok(NULL, "/");
+    }
+  }
+
+  return absolutePath;
+}
+
+string removeLastPathElement(const string path,
+                             const bool removePreSeparator,
+                             const bool removePostSeparator)
+{
+  string newPath = path;
+  size_t offset = newPath.find_last_of(SEPARATOR);
+  if (removePreSeparator &&
+#ifndef _WIN32
+      offset != newPath.find_first_of(SEPARATOR) &&
+#endif
+      offset == newPath.length() - 1) {
+    newPath = newPath.substr(0, offset);
+    offset = newPath.find_last_of(SEPARATOR);
+  }
+  newPath = removePostSeparator ? newPath.substr(0, offset)
+                                : newPath.substr(0, offset + 1);
+  return newPath;
+}
+
+string appendToDirectory(const string& directoryPath, const string& filename)
+{
+  string newPath = directoryPath + SEPARATOR + filename;
+  return newPath;
+}
+
+string getLastPathElement(const string& path)
+{
+  return path.substr(path.find_last_of(SEPARATOR) + 1);
+}
+
+unsigned int getFileSize(const string& path)
+{
+#ifdef _WIN32
+  struct _stat filestatus;
+  _stat(path.c_str(), &filestatus);
+#else
+  struct stat filestatus;
+  stat(path.c_str(), &filestatus);
+#endif
+
+  return filestatus.st_size / 1024;
+}
+
+string getFileSizeAsString(const string& path)
+{
+  ostringstream convert;
+  convert << getFileSize(path);
+  return convert.str();
+}
+
+string getFileContent(const string& path)
+{
+  std::ifstream f(path, std::ios::in|std::ios::ate);
+  std::string content;
+  if (f.is_open()) {
+    auto size = f.tellg();
+    content.reserve(size);
+    f.seekg(0, std::ios::beg);
+    content.assign((std::istreambuf_iterator<char>(f)),
+                    std::istreambuf_iterator<char>());
+  }
+  return content;
+}
+
+bool fileExists(const string& path)
+{
+#ifdef _WIN32
+  return PathFileExists(path.c_str());
+#else
+  bool flag = false;
+  fstream fin;
+  fin.open(path.c_str(), ios::in);
+  if (fin.is_open()) {
+    flag = true;
+  }
+  fin.close();
+  return flag;
+#endif
+}
+
+bool makeDirectory(const string& path)
+{
+#ifdef _WIN32
+  int status = _mkdir(path.c_str());
+#else
+  int status = mkdir(path.c_str(), S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+#endif
+  return status == 0;
+}
+
+string makeTmpDirectory()
+{
+#ifdef _WIN32
+  char cbase[MAX_PATH+1];
+  int base_len = GetTempPath(MAX_PATH+1, cbase);
+  UUID uuid;
+  UuidCreate(&uuid);
+  char* dir_name;
+  UuidToString(&uuid, reinterpret_cast<unsigned char**>(&dir_name));
+  string dir(cbase, base_len);
+  dir += dir_name;
+  _mkdir(dir.c_str());
+  RpcStringFree(reinterpret_cast<unsigned char**>(&dir_name));
+#else
+  string base = "/tmp";
+  auto _template = base + "/kiwix-lib_XXXXXX";
+  char* _template_array = new char[_template.size()+1];
+  memcpy(_template_array, _template.c_str(), _template.size());
+  string dir = mkdtemp(_template_array);
+  delete[] _template_array;
+#endif
+  return dir;
+}
+
+/* Try to create a link and if does not work then make a copy */
+bool copyFile(const string& sourcePath, const string& destPath)
+{
+  try {
+#ifndef _WIN32
+    if (link(sourcePath.c_str(), destPath.c_str()) != 0) {
+#endif
+      std::ifstream infile(sourcePath.c_str(), std::ios_base::binary);
+      std::ofstream outfile(destPath.c_str(), std::ios_base::binary);
+      outfile << infile.rdbuf();
+#ifndef _WIN32
+    }
+#endif
+  } catch (exception& e) {
+    cerr << e.what() << endl;
+    return false;
+  }
+
+  return true;
+}
+
+string getExecutablePath()
+{
+  char binRootPath[PATH_MAX];
+
+#ifdef _WIN32
+  GetModuleFileName(NULL, binRootPath, PATH_MAX);
+  return std::string(binRootPath);
+#elif __APPLE__
+  uint32_t max = (uint32_t)PATH_MAX;
+  _NSGetExecutablePath(binRootPath, &max);
+  return std::string(binRootPath);
+#else
+  ssize_t size = readlink("/proc/self/exe", binRootPath, PATH_MAX);
+  if (size != -1) {
+    return std::string(binRootPath, size);
+  }
+#endif
+
+  return "";
+}
+
+bool writeTextFile(const string& path, const string& content)
+{
+  std::ofstream file;
+  file.open(path.c_str());
+  file << content;
+  file.close();
+  return true;
+}
+
+string getCurrentDirectory()
+{
+  char* a_cwd = getcwd(NULL, 0);
+  string s_cwd(a_cwd);
+  free(a_cwd);
+  return s_cwd;
+}
+
+string getDataDirectory()
+{
+#ifdef _WIN32
+  char* cDataDir = ::getenv("APPDATA");
+#else
+  char* cDataDir = ::getenv("KIWIX_DATA_DIR");
+#endif
+  std::string dataDir = cDataDir==nullptr ? "" : cDataDir;
+  if (!dataDir.empty())
+    return dataDir;
+#ifdef _WIN32
+  cDataDir = ::getenv("USERPROFILE");
+  dataDir = cDataDir==nullptr ? getCurrentDirectory() : cDataDir;
+#else
+  cDataDir = ::getenv("XDG_DATA_HOME");
+  dataDir = cDataDir==nullptr ? "" : cDataDir;
+  if (dataDir.empty()) {
+    cDataDir = ::getenv("HOME");
+    dataDir = cDataDir==nullptr ? getCurrentDirectory() : cDataDir;
+    dataDir = appendToDirectory(dataDir, ".local");
+    dataDir = appendToDirectory(dataDir, "share");
+  }
+#endif
+  return appendToDirectory(dataDir, "kiwix");
+}

src/common/regexTools.cpp

@@ -17,47 +17,41 @@
  * MA 02110-1301, USA.
  */
 
-#include <tools/regexTools.h>
-#include <tools/lock.h>
+#include <common/regexTools.h>
 
-#include <unicode/regex.h>
-#include <unicode/ucnv.h>
+std::map<std::string, icu::RegexMatcher*> regexCache;
 
-#include <memory>
-#include <map>
-#include <pthread.h>
-
-std::map<std::string, std::shared_ptr<icu::RegexPattern>> regexCache;
-static pthread_mutex_t regexLock = PTHREAD_MUTEX_INITIALIZER;
-
-std::unique_ptr<icu::RegexMatcher> buildMatcher(const std::string& regex, icu::UnicodeString& content)
+icu::RegexMatcher* buildRegex(const std::string& regex)
 {
-  std::shared_ptr<icu::RegexPattern> pattern;
+  icu::RegexMatcher* matcher;
+  auto itr = regexCache.find(regex);
+
   /* Regex is in cache */
-  try {
-    pattern = regexCache.at(regex);
-  } catch (std::out_of_range&) {
-    // Redo the search with a lock to avoid race condition.
-    kiwix::Lock l(&regexLock);
-    try {
-      pattern = regexCache.at(regex);
-    } catch (std::out_of_range&) {
-      UErrorCode status = U_ZERO_ERROR;
-      UParseError pe;
-      icu::UnicodeString uregex(regex.c_str());
-      pattern.reset(icu::RegexPattern::compile(uregex, UREGEX_CASE_INSENSITIVE, pe, status));
-      regexCache[regex] = pattern;
-    }
+  if (itr != regexCache.end()) {
+    matcher = itr->second;
   }
-  UErrorCode status = U_ZERO_ERROR;
-  return std::unique_ptr<icu::RegexMatcher>(pattern->matcher(content, status));
+
+  /* Regex needs to be parsed (and cached) */
+  else {
+    UErrorCode status = U_ZERO_ERROR;
+    icu::UnicodeString uregex(regex.c_str());
+    matcher = new icu::RegexMatcher(uregex, UREGEX_CASE_INSENSITIVE, status);
+    regexCache[regex] = matcher;
+  }
+
+  return matcher;
 }
 
+/* todo */
+void freeRegexCache()
+{
+}
 bool matchRegex(const std::string& content, const std::string& regex)
 {
   ucnv_setDefaultName("UTF-8");
   icu::UnicodeString ucontent(content.c_str());
-  auto matcher = buildMatcher(regex, ucontent);
+  auto matcher = buildRegex(regex);
+  matcher->reset(ucontent);
   return matcher->find();
 }
 
@@ -66,9 +60,10 @@ std::string replaceRegex(const std::string& content,
                          const std::string& regex)
 {
   ucnv_setDefaultName("UTF-8");
-  icu::UnicodeString ureplacement(replacement.c_str());
   icu::UnicodeString ucontent(content.c_str());
-  auto matcher = buildMatcher(regex, ucontent);
+  icu::UnicodeString ureplacement(replacement.c_str());
+  auto matcher = buildRegex(regex);
+  matcher->reset(ucontent);
   UErrorCode status = U_ZERO_ERROR;
   auto uresult = matcher->replaceAll(ureplacement, status);
   std::string tmp;
@@ -77,13 +72,15 @@ std::string replaceRegex(const std::string& content,
 }
 
 std::string appendToFirstOccurence(const std::string& content,
-                                   const std::string& regex,
+                                   const std::string regex,
                                    const std::string& replacement)
 {
   ucnv_setDefaultName("UTF-8");
   icu::UnicodeString ucontent(content.c_str());
   icu::UnicodeString ureplacement(replacement.c_str());
-  auto matcher = buildMatcher(regex, ucontent);
+  auto matcher = buildRegex(regex);
+  matcher->reset(ucontent);
+
   if (matcher->find()) {
     UErrorCode status = U_ZERO_ERROR;
     ucontent.insert(matcher->end(status), ureplacement);

src/common/stringTools.cpp

@@ -17,9 +17,8 @@
  * MA 02110-1301, USA.
  */
 
-#include <tools/stringTools.h>
+#include <common/stringTools.h>
 
-#include <tools/pathTools.h>
 #include <unicode/normlzr.h>
 #include <unicode/rep.h>
 #include <unicode/translit.h>
@@ -27,10 +26,6 @@
 #include <unicode/uniset.h>
 #include <unicode/ustring.h>
 
-
-#include <iostream>
-#include <iomanip>
-
 /* tell ICU where to find its dat file (tables) */
 void kiwix::loadICUExternalTables()
 {
@@ -41,7 +36,7 @@ void kiwix::loadICUExternalTables()
       = computeAbsolutePath(executableDirectory, "icudt58l.dat");
   try {
     u_setDataDirectory(datPath.c_str());
-  } catch (std::exception& e) {
+  } catch (exception& e) {
     std::cerr << e.what() << std::endl;
   }
 #endif
@@ -62,6 +57,8 @@ std::string kiwix::removeAccents(const std::string& text)
   return unaccentedText;
 }
 
+#ifndef __ANDROID__
+
 /* Prepare integer for display */
 std::string kiwix::beautifyInteger(uint64_t number)
 {
@@ -141,6 +138,8 @@ std::string kiwix::encodeDiples(const std::string& str)
   return result;
 }
 
+#endif
+
 /* urlEncode() based on javascript encodeURI() &
    encodeURIComponent(). Mostly code from rstudio/httpuv (GPLv3) */
 
@@ -267,42 +266,36 @@ std::string kiwix::urlDecode(const std::string& value, bool component)
 
 /* Split string in a token array */
 std::vector<std::string> kiwix::split(const std::string& str,
-                                      const std::string& delims,
-                                      bool trimEmpty)
+                                      const std::string& delims = " *-")
 {
-  std::string::size_type lastPos = 0;
-  std::string::size_type pos = 0;
+  std::string::size_type lastPos = str.find_first_not_of(delims, 0);
+  std::string::size_type pos = str.find_first_of(delims, lastPos);
   std::vector<std::string> tokens;
-  while( (pos = str.find_first_of(delims, lastPos)) < str.length() )
-  {
-    auto token = str.substr(lastPos, pos - lastPos);
-    if (!trimEmpty || !token.empty()) {
-      tokens.push_back(token);
-    }
-    lastPos = pos + 1;
+
+  while (std::string::npos != pos || std::string::npos != lastPos) {
+    tokens.push_back(str.substr(lastPos, pos - lastPos));
+    lastPos = str.find_first_not_of(delims, pos);
+    pos = str.find_first_of(delims, lastPos);
   }
 
-  auto token = str.substr(lastPos);
-  if (!trimEmpty || !token.empty()) {
-    tokens.push_back(token);
-  }
   return tokens;
 }
 
-std::string kiwix::join(const std::vector<std::string>& list, const std::string& sep)
+std::vector<std::string> kiwix::split(const char* lhs, const char* rhs)
 {
-  std::stringstream ss;
-  bool first = true;
-  for (auto& s:list) {
-    if (!first) {
-      ss << sep;
-    }
-    first = false;
-    ss << s;
-  }
-  return ss.str();
+  const std::string m1(lhs), m2(rhs);
+  return split(m1, m2);
 }
 
+std::vector<std::string> kiwix::split(const char* lhs, const std::string& rhs)
+{
+  return split(lhs, rhs.c_str());
+}
+
+std::vector<std::string> kiwix::split(const std::string& lhs, const char* rhs)
+{
+  return split(lhs.c_str(), rhs);
+}
 
 std::string kiwix::ucFirst(const std::string& word)
 {
@@ -383,11 +376,3 @@ std::string kiwix::normalize(const std::string& word)
 {
   return kiwix::lcAll(word);
 }
-
-
-bool kiwix::startsWith(const std::string& base, const std::string& start)
-{
-   return start.length() <= base.length()
-        && std::equal(start.begin(), start.end(), base.begin());
-}
-

src/config.h.in

@@ -1,3 +1,4 @@
 
 #mesondefine VERSION
 
+#mesondefine ENABLE_CTPP2

src/ctpp2/CTPP2VMStringLoader.cpp

@@ -0,0 +1,210 @@
+/*
+ * Copyright 2013 Renaud Gaudin <reg@kiwix.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU  General Public License as published by
+ * the Free Software Foundation; either version 3 of the License, or
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <ctpp2/CTPP2VMStringLoader.hpp>
+
+namespace CTPP // C++ Template Engine
+{
+
+//
+// Convert byte order
+//
+static void ConvertExecutable(VMExecutable * oCore)
+{
+	// Code entry point
+	oCore -> entry_point = Swap32(oCore -> entry_point);
+	// Offset of code segment
+	oCore -> code_offset = Swap32(oCore -> code_offset);
+
+	// Code segment size
+	oCore -> code_size   = Swap32(oCore -> code_size);
+
+	// Offset of static text segment
+	oCore -> syscalls_offset    = Swap32(oCore -> syscalls_offset);
+	// Static text segment size
+	oCore -> syscalls_data_size = Swap32(oCore -> syscalls_data_size);
+
+	// Offset of static text index segment
+	oCore -> syscalls_index_offset = Swap32(oCore -> syscalls_index_offset);
+	// Static text index segment size
+	oCore -> syscalls_index_size   = Swap32(oCore -> syscalls_index_size);
+
+	// Offset of static data segment
+	oCore -> static_data_offset    = Swap32(oCore -> static_data_offset);
+
+	// Static data segment size
+	oCore -> static_data_data_size = Swap32(oCore -> static_data_data_size);
+
+	// Offset of static text segment
+	oCore -> static_text_offset    = Swap32(oCore -> static_text_offset);
+	// Static text segment size
+	oCore -> static_text_data_size = Swap32(oCore -> static_text_data_size);
+
+	// Offset of static text index segment
+	oCore -> static_text_index_offset = Swap32(oCore -> static_text_index_offset);
+	// Static text index segment size
+	oCore -> static_text_index_size   = Swap32(oCore -> static_text_index_size);
+
+	// Version 2.2+
+	// Offset of static data bit index
+	oCore -> static_data_bit_index_offset = Swap32(oCore -> static_data_bit_index_offset);
+	/// Offset of static data bit index
+	oCore -> static_data_bit_index_size = Swap32(oCore -> static_data_bit_index_size);
+
+	// Platform
+	oCore -> platform      = Swap64(oCore -> platform);
+
+	// Ugly-jolly hack!
+	// ... dereferencing type-punned pointer will break strict-aliasing rules ...
+	UINT_64 iTMP;
+	memcpy(&iTMP, &(oCore -> ieee754double), sizeof(UINT_64));
+	iTMP = Swap64(iTMP);
+	memcpy(&(oCore -> ieee754double), &iTMP, sizeof(UINT_64));
+
+	// Cyclic Redundancy Check
+	oCore -> crc = 0;
+
+	// Convert data structures
+
+	// Convert code segment
+	VMInstruction * pInstructions = const_cast<VMInstruction *>(VMExecutable::GetCodeSeg(oCore));
+	UINT_32 iI = 0;
+	UINT_32 iSteps = oCore -> code_size / sizeof(VMInstruction);
+	for(iI = 0; iI < iSteps; ++iI)
+	{
+		pInstructions -> instruction = Swap32(pInstructions -> instruction);
+		pInstructions -> argument    = Swap32(pInstructions -> argument);
+		pInstructions -> reserved    = Swap64(pInstructions -> reserved);
+		++pInstructions;
+	}
+
+	// Convert syscalls index
+	TextDataIndex * pTextIndex = const_cast<TextDataIndex *>(VMExecutable::GetSyscallsIndexSeg(oCore));
+	iSteps = oCore -> syscalls_index_size / sizeof(TextDataIndex);
+	for(iI = 0; iI < iSteps; ++iI)
+	{
+		pTextIndex -> offset = Swap32(pTextIndex -> offset);
+		pTextIndex -> length = Swap32(pTextIndex -> length);
+		++pTextIndex;
+	}
+
+	// Convert static text index
+	pTextIndex = const_cast<TextDataIndex *>(VMExecutable::GetStaticTextIndexSeg(oCore));
+	iSteps = oCore -> static_text_index_size / sizeof(TextDataIndex);
+	for(iI = 0; iI < iSteps; ++iI)
+	{
+		pTextIndex -> offset = Swap32(pTextIndex -> offset);
+		pTextIndex -> length = Swap32(pTextIndex -> length);
+		++pTextIndex;
+	}
+
+	// Convert static data
+	StaticDataVar * pStaticDataVar = const_cast<StaticDataVar *>(VMExecutable::GetStaticDataSeg(oCore));
+	iSteps = oCore -> static_data_data_size / sizeof(StaticDataVar);
+	for(iI = 0; iI < iSteps; ++iI)
+	{
+		(*pStaticDataVar).i_data = Swap64((*pStaticDataVar).i_data);
+		++pStaticDataVar;
+	}
+}
+
+//
+// Constructor
+//
+VMStringLoader::VMStringLoader(CCHAR_P rawContent, size_t rawContentSize)
+{
+    oCore = (VMExecutable *)malloc(rawContentSize + 1);
+    memcpy(oCore, rawContent, rawContentSize);
+
+	if (oCore -> magic[0] == 'C' &&
+	    oCore -> magic[1] == 'T' &&
+	    oCore -> magic[2] == 'P' &&
+	    oCore -> magic[3] == 'P')
+	{
+		// Check version
+		if (oCore -> version[0] >= 1)
+		{
+			// Platform-dependent data (byte order)
+			if (oCore -> platform == 0x4142434445464748ull)
+			{
+#ifdef _DEBUG
+				fprintf(stderr, "Big/Little Endian conversion: Nothing to do\n");
+#endif
+
+				// Nothing to do, only check crc
+				UINT_32 iCRC = oCore -> crc;
+				oCore -> crc = 0;
+
+				// Calculate CRC of file
+                // KELSON: next line used to refer to oStat.st_size
+                // changed it to rawContentSize
+				if (iCRC != crc32((UCCHAR_P)oCore, rawContentSize))
+				{
+					free(oCore);
+					throw CTPPLogicError("CRC checksum invalid");
+				}
+			}
+			// Platform-dependent data (byte order)
+			else if (oCore -> platform == 0x4847464544434241ull)
+			{
+				// Need to reconvert data
+#ifdef _DEBUG
+				fprintf(stderr, "Big/Little Endian conversion: Need to reconvert core\n");
+#endif
+				ConvertExecutable(oCore);
+			}
+			else
+			{
+				free(oCore);
+				throw CTPPLogicError("Conversion of middle-end architecture does not supported.");
+			}
+
+			// Check IEEE 754 format
+			if (oCore -> ieee754double != 15839800103804824402926068484019465486336.0)
+			{
+				free(oCore);
+				throw CTPPLogicError("IEEE 754 format is broken, cannot convert file");
+			}
+		}
+
+		pVMMemoryCore = new VMMemoryCore(oCore);
+	}
+	else
+	{
+		free(oCore);
+		throw CTPPLogicError("Not an CTPP bytecode file.");
+	}
+}
+
+//
+// Get ready-to-run program
+//
+const VMMemoryCore * VMStringLoader::GetCore() const { return pVMMemoryCore; }
+
+//
+// A destructor
+//
+VMStringLoader::~VMStringLoader() throw()
+{
+	delete pVMMemoryCore;
+	free(oCore);
+}
+
+} // namespace CTPP
+// End.

src/downloader.cpp

@@ -18,8 +18,7 @@
  */
 
 #include "downloader.h"
-#include "tools/pathTools.h"
-#include "tools/stringTools.h"
+#include "common/pathTools.h"
 
 #include <algorithm>
 #include <thread>
@@ -29,7 +28,7 @@
 
 #include "aria2.h"
 #include "xmlrpc.h"
-#include "tools/otherTools.h"
+#include "common/otherTools.h"
 #include <pugixml.hpp>
 
 namespace kiwix
@@ -37,8 +36,6 @@ namespace kiwix
 
 void Download::updateStatus(bool follow)
 {
-  if (m_status == Download::K_REMOVED)
-    return;
   static std::vector<std::string> statusKey = {"status", "files", "totalLength",
                                                "completedLength", "followedBy",
                                                "downloadSpeed", "verifiedLength"};
@@ -96,55 +93,17 @@ void Download::updateStatus(bool follow)
   }
 }
 
-void Download::resumeDownload()
-{
-    if (!m_followedBy.empty())
-        mp_aria->unpause(m_followedBy);
-    else
-        mp_aria->unpause(m_did);
-    updateStatus(true);
-}
-
-void Download::pauseDownload()
-{
-    if (!m_followedBy.empty())
-        mp_aria->pause(m_followedBy);
-    else
-        mp_aria->pause(m_did);
-    updateStatus(true);
-}
-
-void Download::cancelDownload()
-{
-    if (!m_followedBy.empty())
-        mp_aria->remove(m_followedBy);
-    else
-        mp_aria->remove(m_did);
-    m_status = Download::K_REMOVED;
-}
-
 /* Constructor */
 Downloader::Downloader() :
   mp_aria(new Aria2())
 {
-  try {
-    for (auto gid : mp_aria->tellActive()) {
-      m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
-      m_knownDownloads[gid]->updateStatus();
-    }
-  } catch (std::exception& e) {
-    std::cerr << "aria2 tellActive failed : " << e.what();
-  }
-  try {
-    for (auto gid : mp_aria->tellWaiting()) {
-      m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
-      m_knownDownloads[gid]->updateStatus();
-    }
-  } catch (std::exception& e) {
-    std::cerr << "aria2 tellWaiting failed : " << e.what();
+  for (auto gid : mp_aria->tellActive()) {
+    m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
+    m_knownDownloads[gid]->updateStatus();
   }
 }
 
+
 /* Destructor */
 Downloader::~Downloader()
 {
@@ -163,11 +122,6 @@ std::vector<std::string> Downloader::getDownloadIds() {
   return ret;
 }
 
-const std::string &Downloader::getAria2LaunchCmd()
-{
-  return mp_aria->getLaunchCmd();
-}
-
 Download* Downloader::startDownload(const std::string& uri)
 {
   for (auto& p: m_knownDownloads) {
@@ -185,23 +139,14 @@ Download* Downloader::startDownload(const std::string& uri)
 Download* Downloader::getDownload(const std::string& did)
 {
   try {
-    m_knownDownloads.at(did).get()->updateStatus(true);
     return m_knownDownloads.at(did).get();
-  } catch(std::exception& e) {
+  } catch(exception& e) {
     for (auto gid : mp_aria->tellActive()) {
       if (gid == did) {
         m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
-        m_knownDownloads.at(gid).get()->updateStatus(true);
         return m_knownDownloads[gid].get();
       }
     }
-    for (auto gid : mp_aria->tellWaiting()) {
-      if (gid == did) {
-        m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
-        m_knownDownloads.at(gid).get()->updateStatus(true);
-        return m_knownDownloads[gid].get();
-      }
-  }
     throw e;
   }
 }

src/entry.cpp

@@ -122,6 +122,7 @@ Entry Entry::getFinalEntry() const
   if (final_article.good()) {
     return final_article;
   }
+
   int loopCounter = 42;
   final_article = article;
   while (final_article.isRedirect() && loopCounter--) {
@@ -130,10 +131,7 @@ Entry Entry::getFinalEntry() const
       throw NoEntry();
     }
   }
-  // Prevent infinite loops.
-  if (final_article.isRedirect()) {
-    throw NoEntry();
-  }
+
   return final_article;
 }
 

src/kiwixserve.cpp

@@ -1,81 +0,0 @@
-#include "kiwixserve.h"
-#include "subprocess.h"
-
-#ifdef _WIN32
-    # define KIWIXSERVE_CMD "kiwix-serve.exe"
-    # include <windows.h>
-#else
-    # define KIWIXSERVE_CMD "kiwix-serve"
-    # include <unistd.h>
-#endif
-
-#include "tools/pathTools.h"
-#include "tools/stringTools.h"
-
-namespace kiwix {
-
-KiwixServe::KiwixServe(const std::string& libraryPath, int port)
-  : m_port(port),
-    m_libraryPath(libraryPath)
-{
-}
-
-KiwixServe::~KiwixServe()
-{
-    shutDown();
-}
-
-void KiwixServe::run()
-{
-    #ifdef _WIN32
-        int pid = GetCurrentProcessId();
-    #else
-        pid_t pid = getpid();
-
-    #endif
-
-    std::vector<const char*> callCmd;
-    std::string kiwixServeCmd = appendToDirectory(
-        removeLastPathElement(getExecutablePath(true)),
-        KIWIXSERVE_CMD);
-    if (fileExists(kiwixServeCmd)) {
-        // A local kiwix-serve exe exists (packaged with kiwix-desktop), use it.
-        callCmd.push_back(kiwixServeCmd.c_str());
-    } else {
-        // Try to use a potential installed kiwix-serve.
-        callCmd.push_back(KIWIXSERVE_CMD);
-    }
-    std::string attachProcessOpt = "-a" + to_string(pid);
-    std::string portOpt = "-p" + to_string(m_port);
-    callCmd.push_back(attachProcessOpt.c_str());
-    callCmd.push_back(portOpt.c_str());
-    callCmd.push_back("-l");
-    callCmd.push_back(m_libraryPath.c_str());
-    mp_kiwixServe = Subprocess::run(callCmd);
-}
-
-void KiwixServe::shutDown()
-{
-    if (mp_kiwixServe)
-        mp_kiwixServe->kill();
-}
-
-bool KiwixServe::isRunning()
-{
-    if (mp_kiwixServe) {
-        return (mp_kiwixServe->isRunning());
-    }
-    return false;
-}
-
-int KiwixServe::setPort(int port)
-{
-    if (port >= 1 && port <= 65535) {
-        m_port = port;
-    } else {
-        return -1;
-    }
-    return m_port;
-}
-
-}

src/library.cpp

@@ -19,23 +19,18 @@
 
 #include "library.h"
 #include "book.h"
-#include "reader.h"
-#include "libxml_dumper.h"
 
-#include "tools/base64.h"
-#include "tools/regexTools.h"
-#include "tools/pathTools.h"
-#include "tools/stringTools.h"
+#include "common/base64.h"
+#include "common/regexTools.h"
+#include "common/pathTools.h"
 
 #include <pugixml.hpp>
 #include <algorithm>
-#include <set>
 
 namespace kiwix
 {
-
 /* Constructor */
-Library::Library()
+Library::Library() : version(KIWIX_LIBRARY_VERSION)
 {
 }
 /* Destructor */
@@ -48,62 +43,31 @@ bool Library::addBook(const Book& book)
 {
   /* Try to find it */
   try {
-    auto& oldbook = m_books.at(book.getId());
+    auto& oldbook = books.at(book.getId());
     oldbook.update(book);
     return false;
   } catch (std::out_of_range&) {
-    m_books[book.getId()] = book;
+    books[book.getId()] = book;
     return true;
   }
 }
 
-void Library::addBookmark(const Bookmark& bookmark)
-{
-  m_bookmarks.push_back(bookmark);
-}
-
-bool Library::removeBookmark(const std::string& zimId, const std::string& url)
-{
-  for(auto it=m_bookmarks.begin(); it!=m_bookmarks.end(); it++) {
-    if (it->getBookId() == zimId && it->getUrl() == url) {
-      m_bookmarks.erase(it);
-      return true;
-    }
-  }
-  return false;
-}
-
-
 
 bool Library::removeBookById(const std::string& id)
 {
-  return m_books.erase(id) == 1;
+  return books.erase(id) == 1;
 }
 
 Book& Library::getBookById(const std::string& id)
 {
-  return m_books.at(id);
-}
-
-std::shared_ptr<Reader> Library::getReaderById(const std::string& id)
-{
-  try {
-    return m_readers.at(id);
-  } catch (std::out_of_range& e) {}
-
-  auto book = getBookById(id);
-  if (!book.isPathValid())
-    return nullptr;
-  auto sptr = make_shared<Reader>(book.getPath());
-  m_readers[id] = sptr;
-  return sptr;
+  return books.at(id);
 }
 
 unsigned int Library::getBookCount(const bool localBooks,
                                    const bool remoteBooks)
 {
   unsigned int result = 0;
-  for (auto& pair: m_books) {
+  for (auto& pair: books) {
     auto& book = pair.second;
     if ((!book.getPath().empty() && localBooks)
         || (book.getPath().empty() && remoteBooks)) {
@@ -113,18 +77,92 @@ unsigned int Library::getBookCount(const bool localBooks,
   return result;
 }
 
-bool Library::writeToFile(const std::string& path)
-{
-  auto baseDir = removeLastPathElement(path);
-  LibXMLDumper dumper(this);
-  dumper.setBaseDir(baseDir);
-  return writeTextFile(path, dumper.dumpLibXMLContent(getBooksIds()));
-}
+bool Library::writeToFile(const std::string& path) {
+  pugi::xml_document doc;
+  auto baseDir = removeLastPathElement(path, true, false);
 
-bool Library::writeBookmarksToFile(const std::string& path)
-{
-  LibXMLDumper dumper(this);
-  return writeTextFile(path, dumper.dumpLibXMLBookmark());
+  /* Add the library node */
+  pugi::xml_node libraryNode = doc.append_child("library");
+
+  if (!version.empty())
+    libraryNode.append_attribute("version") = version.c_str();
+
+  /* Add each book */
+  for (auto& pair: books) {
+    auto& book = pair.second;
+    if (!book.readOnly()) {
+      pugi::xml_node bookNode = libraryNode.append_child("book");
+      bookNode.append_attribute("id") = book.getId().c_str();
+
+      if (!book.getPath().empty()) {
+        bookNode.append_attribute("path") = computeRelativePath(
+            baseDir, book.getPath()).c_str();
+      }
+
+      if (!book.getIndexPath().empty()) {
+        bookNode.append_attribute("indexPath") = computeRelativePath(
+            baseDir, book.getIndexPath()).c_str();
+        bookNode.append_attribute("indexType") = "xapian";
+      }
+
+      if (book.getOrigId().empty()) {
+        if (!book.getTitle().empty())
+          bookNode.append_attribute("title") = book.getTitle().c_str();
+
+        if (!book.getName().empty())
+          bookNode.append_attribute("name") = book.getName().c_str();
+
+        if (!book.getTags().empty())
+          bookNode.append_attribute("tags") = book.getTags().c_str();
+
+        if (!book.getDescription().empty())
+          bookNode.append_attribute("description") = book.getDescription().c_str();
+
+        if (!book.getLanguage().empty())
+          bookNode.append_attribute("language") = book.getLanguage().c_str();
+
+        if (!book.getCreator().empty())
+          bookNode.append_attribute("creator") = book.getCreator().c_str();
+
+        if (!book.getPublisher().empty())
+          bookNode.append_attribute("publisher") = book.getPublisher().c_str();
+
+        if (!book.getFavicon().empty())
+          bookNode.append_attribute("favicon") = base64_encode(book.getFavicon()).c_str();
+
+        if (!book.getFaviconMimeType().empty())
+          bookNode.append_attribute("faviconMimeType")
+              = book.getFaviconMimeType().c_str();
+      } else {
+        bookNode.append_attribute("origId") = book.getOrigId().c_str();
+      }
+
+      if (!book.getDate().empty()) {
+        bookNode.append_attribute("date") = book.getDate().c_str();
+      }
+
+      if (!book.getUrl().empty()) {
+        bookNode.append_attribute("url") = book.getUrl().c_str();
+      }
+
+      if (book.getArticleCount())
+        bookNode.append_attribute("articleCount") = to_string(book.getArticleCount()).c_str();
+
+      if (book.getMediaCount())
+        bookNode.append_attribute("mediaCount") = to_string(book.getMediaCount()).c_str();
+
+      if (book.getSize()) {
+        bookNode.append_attribute("size") = to_string(book.getSize()>>10).c_str();
+      }
+
+      if (!book.getDownloadId().empty()) {
+        bookNode.append_attribute("downloadId") = book.getDownloadId().c_str();
+      }
+    }
+  }
+
+  /* saving file */
+  return doc.save_file(path.c_str());
 }
 
 std::vector<std::string> Library::getBooksLanguages()
@@ -132,7 +170,7 @@ std::vector<std::string> Library::getBooksLanguages()
   std::vector<std::string> booksLanguages;
   std::map<std::string, bool> booksLanguagesMap;
 
-  for (auto& pair: m_books) {
+  for (auto& pair: books) {
     auto& book = pair.second;
     auto& language = book.getLanguage();
     if (booksLanguagesMap.find(language) == booksLanguagesMap.end()) {
@@ -151,7 +189,7 @@ std::vector<std::string> Library::getBooksCreators()
   std::vector<std::string> booksCreators;
   std::map<std::string, bool> booksCreatorsMap;
 
-  for (auto& pair: m_books) {
+  for (auto& pair: books) {
     auto& book = pair.second;
     auto& creator = book.getCreator();
     if (booksCreatorsMap.find(creator) == booksCreatorsMap.end()) {
@@ -170,7 +208,7 @@ std::vector<std::string> Library::getBooksPublishers()
   std::vector<std::string> booksPublishers;
   std::map<std::string, bool> booksPublishersMap;
 
-  for (auto& pair:m_books) {
+  for (auto& pair:books) {
     auto& book = pair.second;
     auto& publisher = book.getPublisher();
     if (booksPublishersMap.find(publisher) == booksPublishersMap.end()) {
@@ -184,26 +222,11 @@ std::vector<std::string> Library::getBooksPublishers()
   return booksPublishers;
 }
 
-const std::vector<kiwix::Bookmark> Library::getBookmarks(bool onlyValidBookmarks)
-{
-  if (!onlyValidBookmarks) {
-    return m_bookmarks;
-  }
-  std::vector<kiwix::Bookmark> validBookmarks;
-  auto booksId = getBooksIds();
-  for(auto& bookmark:m_bookmarks) {
-    if (std::find(booksId.begin(), booksId.end(), bookmark.getBookId()) != booksId.end()) {
-      validBookmarks.push_back(bookmark);
-    }
-  }
-  return validBookmarks;
-}
-
 std::vector<std::string> Library::getBooksIds()
 {
   std::vector<std::string> bookIds;
 
-  for (auto& pair: m_books) {
+  for (auto& pair: books) {
     bookIds.push_back(pair.first);
   }
 
@@ -216,104 +239,67 @@ std::vector<std::string> Library::filter(const std::string& search)
     return getBooksIds();
   }
 
-  return filter(Filter().query(search));
-}
-
-
-std::vector<std::string> Library::filter(const Filter& filter)
-{
   std::vector<std::string> bookIds;
-  for(auto& pair:m_books) {
-    auto book = pair.second;
-    if(filter.accept(book)) {
-      bookIds.push_back(pair.first);
-    }
+  for(auto& pair:books) {
+     auto& book = pair.second;
+     if (matchRegex(book.getTitle(), "\\Q" + search + "\\E")
+         || matchRegex(book.getDescription(), "\\Q" + search + "\\E")) {
+       bookIds.push_back(pair.first);
+     }
   }
+
   return bookIds;
 }
 
-template<supportedListSortBy SORT>
-struct KEY_TYPE {
-  typedef std::string TYPE;
-};
-
-template<>
-struct KEY_TYPE<SIZE> {
-  typedef size_t TYPE;
-};
-
 template<supportedListSortBy sort>
-class Comparator {
-  private:
-    Library* lib;
-    bool     ascending;
+struct Comparator {
+  Library* lib;
+  Comparator(Library* lib) : lib(lib) {}
 
-    inline typename KEY_TYPE<sort>::TYPE get_key(const std::string& id);
+  bool operator() (const std::string& id1, const std::string& id2) {
+    return get_keys(id1) < get_keys(id2);
+  }
 
-  public:
-    Comparator(Library* lib, bool ascending) : lib(lib), ascending(ascending) {}
-    inline bool operator() (const std::string& id1, const std::string& id2) {
-      if (ascending) {
-        return get_key(id1) < get_key(id2);
-      } else {
-        return get_key(id2) < get_key(id1);
-      }
-    }
+  std::string get_keys(const std::string& id);
+  unsigned int get_keyi(const std::string& id);
 };
 
 template<>
-std::string Comparator<TITLE>::get_key(const std::string& id)
+std::string Comparator<TITLE>::get_keys(const std::string& id)
 {
   return lib->getBookById(id).getTitle();
 }
 
 template<>
-size_t Comparator<SIZE>::get_key(const std::string& id)
+unsigned int Comparator<SIZE>::get_keyi(const std::string& id)
 {
   return lib->getBookById(id).getSize();
 }
 
 template<>
-std::string Comparator<DATE>::get_key(const std::string& id)
+bool Comparator<SIZE>::operator() (const std::string& id1, const std::string& id2)
+{
+  return get_keyi(id1) < get_keyi(id2);
+}
+
+template<>
+std::string Comparator<DATE>::get_keys(const std::string& id)
 {
   return lib->getBookById(id).getDate();
 }
 
 template<>
-std::string Comparator<CREATOR>::get_key(const std::string& id)
+std::string Comparator<CREATOR>::get_keys(const std::string& id)
 {
   return lib->getBookById(id).getCreator();
 }
 
 template<>
-std::string Comparator<PUBLISHER>::get_key(const std::string& id)
+std::string Comparator<PUBLISHER>::get_keys(const std::string& id)
 {
   return lib->getBookById(id).getPublisher();
 }
 
-void Library::sort(std::vector<std::string>& bookIds, supportedListSortBy sort, bool ascending)
-{
-  switch(sort) {
-    case TITLE:
-      std::sort(bookIds.begin(), bookIds.end(), Comparator<TITLE>(this, ascending));
-      break;
-    case SIZE:
-      std::sort(bookIds.begin(), bookIds.end(), Comparator<SIZE>(this, ascending));
-      break;
-    case DATE:
-      std::sort(bookIds.begin(), bookIds.end(), Comparator<DATE>(this, ascending));
-      break;
-    case CREATOR:
-      std::sort(bookIds.begin(), bookIds.end(), Comparator<CREATOR>(this, ascending));
-      break;
-    case PUBLISHER:
-      std::sort(bookIds.begin(), bookIds.end(), Comparator<PUBLISHER>(this, ascending));
-      break;
-    default:
-      break;
-  }
-}
-
 
 std::vector<std::string> Library::listBooksIds(
     int mode,
@@ -322,208 +308,59 @@ std::vector<std::string> Library::listBooksIds(
     const std::string& language,
     const std::string& creator,
     const std::string& publisher,
-    const std::vector<std::string>& tags,
     size_t maxSize) {
 
-  Filter _filter;
-  if (mode & LOCAL)
-    _filter.local(true);
-  if (mode & NOLOCAL)
-    _filter.local(false);
-  if (mode & VALID)
-    _filter.valid(true);
-  if (mode & NOVALID)
-    _filter.valid(false);
-  if (mode & REMOTE)
-    _filter.remote(true);
-  if (mode & NOREMOTE)
-    _filter.remote(false);
-  if (!tags.empty())
-    _filter.acceptTags(tags);
-  if (maxSize != 0)
-    _filter.maxSize(maxSize);
-  if (!language.empty())
-    _filter.lang(language);
-  if (!publisher.empty())
-    _filter.publisher(publisher);
-  if (!creator.empty())
-    _filter.creator(creator);
-  if (!search.empty())
-    _filter.query(search);
+  std::vector<std::string> bookIds;
+  for(auto& pair:books) {
+    auto& book = pair.second;
+    auto local = !book.getPath().empty();
+    if (mode & LOCAL && !local)
+      continue;
+    if (mode & NOLOCAL && local)
+      continue;
+    auto valid = book.isPathValid();
+    if (mode & VALID && !valid)
+      continue;
+    if (mode & NOVALID && valid)
+      continue;
+    auto remote = !book.getUrl().empty();
+    if (mode & REMOTE && !remote)
+      continue;
+    if (mode & NOREMOTE && remote)
+      continue;
+    if (maxSize != 0 && book.getSize() > maxSize)
+      continue;
+    if (!language.empty() && book.getLanguage() != language)
+      continue;
+    if (!publisher.empty() && book.getPublisher() != publisher)
+      continue;
+    if (!creator.empty() && book.getCreator() != creator)
+      continue;
+    if (!search.empty() && !(matchRegex(book.getTitle(), "\\Q" + search + "\\E")
+                          || matchRegex(book.getDescription(), "\\Q" + search + "\\E")))
+      continue;
+    bookIds.push_back(pair.first);
+  }
 
-  auto bookIds = filter(_filter);
-
-  sort(bookIds, sortBy, true);
+  switch(sortBy) {
+    case TITLE:
+      std::sort(bookIds.begin(), bookIds.end(), Comparator<TITLE>(this));
+      break;
+    case SIZE:
+      std::sort(bookIds.begin(), bookIds.end(), Comparator<SIZE>(this));
+      break;
+    case DATE:
+      std::sort(bookIds.begin(), bookIds.end(), Comparator<DATE>(this));
+      break;
+    case CREATOR:
+      std::sort(bookIds.begin(), bookIds.end(), Comparator<CREATOR>(this));
+      break;
+    case PUBLISHER:
+      std::sort(bookIds.begin(), bookIds.end(), Comparator<PUBLISHER>(this));
+      break;
+    default:
+      break;
+  }
   return bookIds;
 }
-
-Filter::Filter()
-  : activeFilters(0),
-    _maxSize(0)
-{};
-
-#define FLAG(x) (1 << x)
-enum filterTypes {
-  NONE = 0,
-  _LOCAL = FLAG(0),
-  _REMOTE = FLAG(1),
-  _NOLOCAL = FLAG(2),
-  _NOREMOTE = FLAG(3),
-  _VALID = FLAG(4),
-  _NOVALID = FLAG(5),
-  ACCEPTTAGS = FLAG(6),
-  REJECTTAGS = FLAG(7),
-  LANG = FLAG(8),
-  _PUBLISHER = FLAG(9),
-  _CREATOR = FLAG(10),
-  MAXSIZE = FLAG(11),
-  QUERY = FLAG(12),
-};
-
-Filter& Filter::local(bool accept)
-{
-  if (accept) {
-    activeFilters |= _LOCAL;
-    activeFilters &= ~_NOLOCAL;
-  } else {
-    activeFilters |= _NOLOCAL;
-    activeFilters &= ~_LOCAL;
-  }
-  return *this;
-}
-
-Filter& Filter::remote(bool accept)
-{
-  if (accept) {
-    activeFilters |= _REMOTE;
-    activeFilters &= ~_NOREMOTE;
-  } else {
-    activeFilters |= _NOREMOTE;
-    activeFilters &= ~_REMOTE;
-  }
-  return *this;
-}
-
-Filter& Filter::valid(bool accept)
-{
-  if (accept) {
-    activeFilters |= _VALID;
-    activeFilters &= ~_NOVALID;
-  } else {
-    activeFilters |= _NOVALID;
-    activeFilters &= ~_VALID;
-  }
-  return *this;
-}
-
-Filter& Filter::acceptTags(std::vector<std::string> tags)
-{
-  _acceptTags = tags;
-  activeFilters |= ACCEPTTAGS;
-  return *this;
-}
-
-Filter& Filter::rejectTags(std::vector<std::string> tags)
-{
-  _rejectTags = tags;
-  activeFilters |= REJECTTAGS;
-  return *this;
-}
-
-Filter& Filter::lang(std::string lang)
-{
-  _lang = lang;
-  activeFilters |= LANG;
-  return *this;
-}
-
-Filter& Filter::publisher(std::string publisher)
-{
-  _publisher = publisher;
-  activeFilters |= _PUBLISHER;
-  return *this;
-}
-
-Filter& Filter::creator(std::string creator)
-{
-  _creator = creator;
-  activeFilters |= _CREATOR;
-  return *this;
-}
-
-Filter& Filter::maxSize(size_t maxSize)
-{
-  _maxSize = maxSize;
-  activeFilters |= MAXSIZE;
-  return *this;
-}
-
-Filter& Filter::query(std::string query)
-{
-  _query = query;
-  activeFilters |= QUERY;
-  return *this;
-}
-
-#define ACTIVE(X) (activeFilters & (X))
-bool Filter::accept(const Book& book) const
-{
-  auto local = !book.getPath().empty();
-  if (ACTIVE(_LOCAL) && !local)
-    return false;
-  if (ACTIVE(_NOLOCAL) && local)
-    return false;
-  auto valid = book.isPathValid();
-  if (ACTIVE(_VALID) && !valid)
-    return false;
-  if (ACTIVE(_NOVALID) && valid)
-    return false;
-  auto remote = !book.getUrl().empty();
-  if (ACTIVE(_REMOTE) && !remote)
-    return false;
-  if (ACTIVE(_NOREMOTE) && remote)
-    return false;
-  if (ACTIVE(ACCEPTTAGS)) {
-    if (!_acceptTags.empty()) {
-      auto vBookTags = split(book.getTags(), ";");
-      std::set<std::string> sBookTags(vBookTags.begin(), vBookTags.end());
-      for (auto& t: _acceptTags) {
-        if (sBookTags.find(t) == sBookTags.end()) {
-          return false;
-        }
-      }
-    }
-  }
-  if (ACTIVE(REJECTTAGS)) {
-    if (!_rejectTags.empty()) {
-      auto vBookTags = split(book.getTags(), ";");
-      std::set<std::string> sBookTags(vBookTags.begin(), vBookTags.end());
-      for (auto& t: _rejectTags) {
-        if (sBookTags.find(t) != sBookTags.end()) {
-          return false;
-        }
-      }
-    }
-  }
-  if (ACTIVE(MAXSIZE) && book.getSize() > _maxSize)
-    return false;
-
-  if (ACTIVE(LANG) && book.getLanguage() != _lang)
-    return false;
-
-  if (ACTIVE(_PUBLISHER) && book.getPublisher() != _publisher)
-    return false;
-
-  if (ACTIVE(_CREATOR) && book.getCreator() != _creator)
-    return false;
-
-  if ( ACTIVE(QUERY)
-    && !(matchRegex(book.getTitle(), "\\Q" + _query + "\\E")
-        || matchRegex(book.getDescription(), "\\Q" + _query + "\\E")))
-    return false;
-
-  return true;
-
-}
-
 }

src/libxml_dumper.cpp

@@ -1,140 +0,0 @@
-/*
- * Copyright 2017 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "libxml_dumper.h"
-#include "book.h"
-
-#include "tools/base64.h"
-#include "tools/stringTools.h"
-#include "tools/otherTools.h"
-#include "tools/pathTools.h"
-
-namespace kiwix
-{
-/* Constructor */
-LibXMLDumper::LibXMLDumper(Library* library)
-  : library(library)
-{
-}
-/* Destructor */
-LibXMLDumper::~LibXMLDumper()
-{
-}
-
-#define ADD_ATTRIBUTE(node, name, value) { (node).append_attribute((name)) = (value).c_str(); }
-#define ADD_ATTR_NOT_EMPTY(node, name, value) { if (!(value).empty()) ADD_ATTRIBUTE(node, name, value); }
-
-void LibXMLDumper::handleBook(Book book, pugi::xml_node root_node) {
-  if (book.readOnly())
-    return;
-
-  auto entry_node = root_node.append_child("book");
-  ADD_ATTRIBUTE(entry_node, "id", book.getId());
-
-  if (!book.getPath().empty()) {
-    ADD_ATTRIBUTE(entry_node, "path", computeRelativePath(baseDir, book.getPath()));
-  }
-
-  if (book.getOrigId().empty()) {
-    ADD_ATTR_NOT_EMPTY(entry_node, "title", book.getTitle());
-    ADD_ATTR_NOT_EMPTY(entry_node, "name", book.getName());
-    ADD_ATTR_NOT_EMPTY(entry_node, "tags", book.getTags());
-    ADD_ATTR_NOT_EMPTY(entry_node, "description", book.getDescription());
-    ADD_ATTR_NOT_EMPTY(entry_node, "language", book.getLanguage());
-    ADD_ATTR_NOT_EMPTY(entry_node, "creator", book.getCreator());
-    ADD_ATTR_NOT_EMPTY(entry_node, "publisher", book.getPublisher());
-    ADD_ATTR_NOT_EMPTY(entry_node, "faviconMimeType", book.getFaviconMimeType());
-    if (!book.getFavicon().empty())
-      ADD_ATTRIBUTE(entry_node, "favicon", base64_encode(book.getFavicon()));
-  } else {
-    ADD_ATTRIBUTE(entry_node, "origId", book.getOrigId());
-  }
-
-  ADD_ATTR_NOT_EMPTY(entry_node, "date", book.getDate());
-  ADD_ATTR_NOT_EMPTY(entry_node, "url", book.getUrl());
-
-  if (book.getArticleCount())
-    ADD_ATTRIBUTE(entry_node, "articleCount", to_string(book.getArticleCount()));
-
-  if (book.getMediaCount())
-    ADD_ATTRIBUTE(entry_node, "mediaCount", to_string(book.getMediaCount()));
-
-  if (book.getSize())
-    ADD_ATTRIBUTE(entry_node, "size", to_string(book.getSize()>>10));
-
-  ADD_ATTR_NOT_EMPTY(entry_node, "downloadId", book.getDownloadId());
-}
-
-#define ADD_TEXT_ENTRY(node, child, value) (node).append_child((child)).append_child(pugi::node_pcdata).set_value((value).c_str())
-
-void LibXMLDumper::handleBookmark(Bookmark bookmark, pugi::xml_node root_node) {
-
-  auto entry_node = root_node.append_child("bookmark");
-  auto book_node = entry_node.append_child("book");
-
-  try {
-    auto book = library->getBookById(bookmark.getBookId());
-    ADD_TEXT_ENTRY(book_node, "id", book.getId());
-    ADD_TEXT_ENTRY(book_node, "title", book.getTitle());
-    ADD_TEXT_ENTRY(book_node, "language", book.getLanguage());
-    ADD_TEXT_ENTRY(book_node, "date", book.getDate());
-  } catch (...) {
-    ADD_TEXT_ENTRY(book_node, "id", bookmark.getBookId());
-    ADD_TEXT_ENTRY(book_node, "title", bookmark.getBookTitle());
-    ADD_TEXT_ENTRY(book_node, "language", bookmark.getLanguage());
-    ADD_TEXT_ENTRY(book_node, "date", bookmark.getDate());
-  }
-  ADD_TEXT_ENTRY(entry_node, "title", bookmark.getTitle());
-  ADD_TEXT_ENTRY(entry_node, "url", bookmark.getUrl());
-}
-
-
-std::string LibXMLDumper::dumpLibXMLContent(const std::vector<std::string>& bookIds)
-{
-  pugi::xml_document doc;
-
-  /* Add the library node */
-  pugi::xml_node libraryNode = doc.append_child("library");
-
-  libraryNode.append_attribute("version") = KIWIX_LIBRARY_VERSION;
-
-  if (library) {
-    for (auto& bookId: bookIds) {
-      handleBook(library->getBookById(bookId), libraryNode);
-    }
-  }
-  return nodeToString(libraryNode);
-}
-
-std::string LibXMLDumper::dumpLibXMLBookmark()
-{
-  pugi::xml_document doc;
-
-  /* Add the library node */
-  pugi::xml_node bookmarksNode = doc.append_child("bookmarks");
-
-  if (library) {
-    for (auto& bookmark: library->getBookmarks()) {
-      handleBookmark(bookmark, bookmarksNode);
-    }
-  }
-  return nodeToString(bookmarksNode);
-}
-
-}

src/manager.cpp

@@ -59,7 +59,7 @@ bool Manager::parseXmlDom(const pugi::xml_document& doc,
 
     book.setReadOnly(readOnly);
     book.updateFromXml(bookNode,
-                       removeLastPathElement(libraryPath));
+                       removeLastPathElement(libraryPath, true, false));
 
     /* Update the book properties with the new importer */
     if (libraryVersion.empty()
@@ -177,7 +177,7 @@ std::string Manager::addBookFromPathAndGetId(const std::string& pathToOpen,
     if (pathToSave != pathToOpen) {
       book.setPath(isRelativePath(pathToSave)
                 ? computeAbsolutePath(
-                      removeLastPathElement(writableLibraryPath),
+                      removeLastPathElement(writableLibraryPath, true, false),
                       pathToSave)
                 : pathToSave);
     }
@@ -208,15 +208,12 @@ bool Manager::addBookFromPath(const std::string& pathToOpen,
 
 bool Manager::readBookFromPath(const std::string& path, kiwix::Book* book)
 {
-  std::string tmp_path = path;
-  if (isRelativePath(path)) {
-    tmp_path = computeAbsolutePath(getCurrentDirectory(), path);
-  }
   try {
-    kiwix::Reader reader(tmp_path);
+    kiwix::Reader reader(path);
     book->update(reader);
     book->setPathValid(true);
   } catch (const std::exception& e) {
+    std::cerr << "Invalid " << path << " : " << e.what() << std::endl;
     book->setPathValid(false);
     return false;
   }
@@ -224,27 +221,4 @@ bool Manager::readBookFromPath(const std::string& path, kiwix::Book* book)
   return true;
 }
 
-bool Manager::readBookmarkFile(const std::string& path)
-{
-  pugi::xml_document doc;
-  pugi::xml_parse_result result = doc.load_file(path.c_str());
-
-  if (!result) {
-    return false;
-  }
-
-  pugi::xml_node libraryNode = doc.child("bookmarks");
-
-  for (pugi::xml_node node = libraryNode.child("bookmark"); node;
-       node = node.next_sibling("bookmark")) {
-    kiwix::Bookmark bookmark;
-
-    bookmark.updateFromXml(node);
-
-    manipulator->addBookmarkToLibrary(bookmark);
-  }
-
-  return true;
-}
-
 }

src/meson.build

@@ -1,28 +1,22 @@
 kiwix_sources = [
   'book.cpp',
-  'bookmark.cpp',
   'library.cpp',
   'manager.cpp',
-  'libxml_dumper.cpp',
   'opds_dumper.cpp',
   'downloader.cpp',
   'reader.cpp',
   'entry.cpp',
-  'server.cpp',
   'searcher.cpp',
-  'search_renderer.cpp',
   'subprocess.cpp',
   'aria2.cpp',
-  'tools/base64.cpp',
-  'tools/pathTools.cpp',
-  'tools/regexTools.cpp',
-  'tools/stringTools.cpp',
-  'tools/networkTools.cpp',
-  'tools/otherTools.cpp',
-  'kiwixserve.cpp',
-  'name_mapper.cpp',
-  'server/request_context.cpp',
-  'server/response.cpp'
+  'common/base64.cpp',
+  'common/pathTools.cpp',
+  'common/regexTools.cpp',
+  'common/stringTools.cpp',
+  'common/networkTools.cpp',
+  'common/otherTools.cpp',
+  'xapian/htmlparse.cc',
+  'xapian/myhtmlparse.cc'
 ]
 kiwix_sources += lib_resources
 
@@ -32,6 +26,10 @@ else
   kiwix_sources += 'subprocess_unix.cpp'
 endif
 
+if xapian_dep.found()
+  kiwix_sources += ['xapianSearcher.cpp']
+endif
+
 if get_option('android')
   subdir('android')
   install_dir = 'kiwix-lib/jniLibs/' + meson.get_cross_property('android_abi')
@@ -39,6 +37,11 @@ else
   install_dir = get_option('libdir')
 endif
 
+
+if has_ctpp2_dep
+  kiwix_sources += ['ctpp2/CTPP2VMStringLoader.cpp']
+endif
+
 config_h = configure_file(output : 'kiwix_config.h',
                configuration : conf,
                input : 'config.h.in')
@@ -50,4 +53,5 @@ kiwixlib = library('kiwix',
                    dependencies : all_deps,
                    version: meson.project_version(),
                    install: true,
-                   install_dir: install_dir)
+                   install_dir: install_dir,
+                   install_rpath: '$ORIGIN')

src/name_mapper.cpp

@@ -1,62 +0,0 @@
-/*
- * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "name_mapper.h"
-#include "library.h"
-#include "tools/regexTools.h"
-#include <iostream>
-
-namespace kiwix {
-
-HumanReadableNameMapper::HumanReadableNameMapper(kiwix::Library& library, bool withAlias) {
-  for (auto& bookId: library.filter(kiwix::Filter().local(true).valid(true))) {
-    auto& currentBook = library.getBookById(bookId);
-    auto bookName = currentBook.getHumanReadableIdFromPath();
-    m_idToName[bookId] = bookName;
-    m_nameToId[bookName] = bookId;
-
-    if (!withAlias)
-      continue;
-
-    auto aliasName = replaceRegex(bookName, "", "_[[:digit:]]{4}-[[:digit:]]{2}$");
-    if (aliasName == bookName) {
-      continue;
-    }
-    if (m_nameToId.find(aliasName) == m_nameToId.end()) {
-      m_nameToId[aliasName] = bookId;
-    } else {
-      auto alreadyPresentPath = library.getBookById(m_nameToId[aliasName]).getPath();
-      std::cerr << "Path collision: " << alreadyPresentPath
-                << " and " << currentBook.getPath()
-                << " can't share the same URL path '" << aliasName << "'."
-                << " Therefore, only " << alreadyPresentPath
-                << " will be served." << std::endl;
-    }
-  }
-}
-
-std::string HumanReadableNameMapper::getNameForId(const std::string& id) {
-  return m_idToName.at(id);
-}
-
-std::string HumanReadableNameMapper::getIdForName(const std::string& name) {
-  return m_nameToId.at(name);
-}
-
-}

src/opds_dumper.cpp

@@ -20,8 +20,7 @@
 #include "opds_dumper.h"
 #include "book.h"
 
-#include "tools/otherTools.h"
-#include <iomanip>
+#include <common/otherTools.h>
 
 namespace kiwix
 {
@@ -51,13 +50,6 @@ std::string gen_date_str()
   return is.str();
 }
 
-static std::string gen_date_from_yyyy_mm_dd(const std::string& date)
-{
-  std::stringstream is;
-  is << date << "T00:00::00:Z";
-  return is.str();
-}
-
 void OPDSDumper::setOpenSearchInfo(int totalResults, int startIndex, int count)
 {
   m_totalResults = totalResults;
@@ -73,9 +65,8 @@ pugi::xml_node OPDSDumper::handleBook(Book book, pugi::xml_node root_node) {
   ADD_TEXT_ENTRY(entry_node, "title", book.getTitle());
   ADD_TEXT_ENTRY(entry_node, "id", "urn:uuid:"+book.getId());
   ADD_TEXT_ENTRY(entry_node, "icon", rootLocation + "/meta?name=favicon&content=" + book.getHumanReadableIdFromPath());
-  ADD_TEXT_ENTRY(entry_node, "updated", gen_date_from_yyyy_mm_dd(book.getDate()));
+  ADD_TEXT_ENTRY(entry_node, "updated", date);
   ADD_TEXT_ENTRY(entry_node, "summary", book.getDescription());
-  ADD_TEXT_ENTRY(entry_node, "tags", book.getTags());
 
   auto content_node = entry_node.append_child("link");
   content_node.append_attribute("type") = "text/html";

src/reader.cpp

@@ -241,6 +241,8 @@ Entry Reader::getMainPage() const
     throw NoEntry();
   }
 
+  string url = "";
+
   zim::Article article;
   if (this->zimFileHandler->getFileheader().hasMainPage())
   {
@@ -258,7 +260,7 @@ Entry Reader::getMainPage() const
 
 bool Reader::getFavicon(string& content, string& mimeType) const
 {
-  static const char* const paths[] = {"-/favicon", "-/favicon.png", "I/favicon.png", "I/favicon"};
+  static const char* const paths[] = {"-/favicon.png", "I/favicon.png", "I/favicon", "-/favicon"};
 
   for (auto &path: paths) {
     try {
@@ -278,7 +280,7 @@ string Reader::getZimFilePath() const
   return this->zimFilePath;
 }
 /* Return a metatag value */
-bool Reader::getMetadata(const string& name, string& value) const
+bool Reader::getMetatag(const string& name, string& value) const
 {
   try {
     auto entry = getEntryFromPath("M/"+name);
@@ -289,17 +291,10 @@ bool Reader::getMetadata(const string& name, string& value) const
   }
 }
 
-#define METADATA(NAME) std::string v; getMetadata(NAME, v); return v;
-
-string Reader::getName() const
-{
-  METADATA("Name")
-}
-
 string Reader::getTitle() const
 {
   string value;
-  this->getMetadata("Title", value);
+  this->getMetatag("Title", value);
   if (value.empty()) {
     value = getLastPathElement(zimFileHandler->getFilename());
     std::replace(value.begin(), value.end(), '_', ' ');
@@ -309,164 +304,65 @@ string Reader::getTitle() const
   return value;
 }
 
-string Reader::getCreator() const
+string Reader::getName() const
 {
-  METADATA("Creator")
+  string value;
+  this->getMetatag("Name", value);
+  return value;
 }
 
-string Reader::getPublisher() const
+string Reader::getTags() const
 {
-  METADATA("Publisher")
-}
-
-string Reader::getDate() const
-{
-  METADATA("Date")
+  string value;
+  this->getMetatag("Tags", value);
+  return value;
 }
 
 string Reader::getDescription() const
 {
   string value;
-  this->getMetadata("Description", value);
+  this->getMetatag("Description", value);
 
   /* Mediawiki Collection tends to use the "Subtitle" name */
   if (value.empty()) {
-    this->getMetadata("Subtitle", value);
+    this->getMetatag("Subtitle", value);
   }
 
   return value;
 }
 
-string Reader::getLongDescription() const
-{
-  METADATA("LongDescription")
-}
-
 string Reader::getLanguage() const
 {
-  METADATA("Language")
+  string value;
+  this->getMetatag("Language", value);
+  return value;
 }
 
-string Reader::getLicense() const
+string Reader::getDate() const
 {
-  METADATA("License")
+  string value;
+  this->getMetatag("Date", value);
+  return value;
 }
 
-std::vector<std::string> convertTags(const std::string& tags_str)
+string Reader::getCreator() const
 {
-  auto tags = split(tags_str, ";");
-  std::vector<std::string> tagsList;
-  bool picSeen(false), vidSeen(false), detSeen(false), indexSeen(false);
-  for (auto tag: tags) {
-    picSeen |= (tag == "nopic" || startsWith(tag, "_pictures:"));
-    vidSeen |= (tag == "novid" || startsWith(tag, "_videos:"));
-    detSeen |= (tag == "nodet" || startsWith(tag, "_details:"));
-    indexSeen |= startsWith(tag, "_ftindex");
-    if (tag == "nopic") {
-      tagsList.push_back("_pictures:no");
-    } else if (tag == "novid") {
-      tagsList.push_back("_videos:no");
-    } else if (tag == "nodet") {
-      tagsList.push_back("_details:no");
-    } else if (tag == "_ftindex") {
-      tagsList.push_back("_ftindex:yes");
-    } else {
-      tagsList.push_back(tag);
-    }
-  }
-  if (!indexSeen) {
-    tagsList.push_back("_ftindex:no");
-  }
-  if (!picSeen) {
-    tagsList.push_back("_pictures:yes");
-  }
-  if (!vidSeen) {
-    tagsList.push_back("_videos:yes");
-  }
-  if (!detSeen) {
-    tagsList.push_back("_details:yes");
-  }
-  return tagsList;
+  string value;
+  this->getMetatag("Creator", value);
+  return value;
 }
 
-string Reader::getTags(bool original) const
+string Reader::getPublisher() const
 {
-  string tags_str;
-  getMetadata("Tags", tags_str);
-  if (original) {
-    return tags_str;
-  }
-  auto tags = convertTags(tags_str);
-  return join(tags, ";");
+  string value;
+  this->getMetatag("Publisher", value);
+  return value;
 }
 
-string getTagValueFromTagList(const std::vector<std::string>& tagList, const std::string& tagName)
-{
-  for (auto tag: tagList) {
-    if (tag[0] == '_') {
-      auto delimPos = tag.find(':');
-      if (delimPos == string::npos) {
-        // No delimiter... what to do ?
-        continue;
-      }
-      auto cTagName = tag.substr(1, delimPos-1);
-      auto cTagValue = tag.substr(delimPos+1);
-      if (cTagName == tagName) {
-        return cTagValue;
-      }
-    }
-  }
-  std::stringstream ss;
-  ss << tagName << " cannot be found";
-  throw std::out_of_range(ss.str());
-}
-
-string Reader::getTagStr(const std::string& tagName) const
-{
-  string tags_str;
-  getMetadata("Tags", tags_str);
-  return getTagValueFromTagList(convertTags(tags_str), tagName);
-}
-
-bool Reader::getTagBool(const std::string& tagName) const
-{
-  auto tagValue = getTagStr(tagName);
-  if (tagValue == "yes") {
-    return true;
-  } else if (tagValue == "no") {
-    return false;
-  } else {
-    std::stringstream ss;
-    ss << "Tag value '" << tagValue << "' for " << tagName << " cannot be converted to bool.";
-    throw std::domain_error(ss.str());
-  }
-}
-
-string Reader::getRelation() const
-{
-  METADATA("Relation")
-}
-
-string Reader::getFlavour() const
-{
-  METADATA("Flavour")
-}
-
-string Reader::getSource() const
-{
-  METADATA("Source")
-}
-
-string Reader::getScraper() const
-{
-  METADATA("Scraper")
-}
-#undef METADATA
-
 string Reader::getOrigId() const
 {
   string value;
-  this->getMetadata("startfileuid", value);
+  this->getMetatag("startfileuid", value);
   if (value.empty()) {
     return "";
   }
@@ -866,21 +762,18 @@ bool Reader::searchSuggestionsSmart(const string& prefix,
                                     unsigned int suggestionsCount)
 {
   std::vector<std::string> variants = this->getTitleVariants(prefix);
-  bool retVal = false;
+  bool retVal;
 
   this->suggestions.clear();
   this->suggestionsOffset = this->suggestions.begin();
   /* Try to search in the title using fulltext search database */
-  const auto suggestionSearch
+  const zim::Search* suggestionSearch
       = this->getZimFileHandler()->suggestions(prefix, 0, suggestionsCount);
 
   if (suggestionSearch->get_matches_estimated()) {
     for (auto current = suggestionSearch->begin();
          current != suggestionSearch->end();
          current++) {
-      if (!current->good()) {
-          continue;
-      }
       std::vector<std::string> suggestion;
       suggestion.push_back(current->getTitle());
       suggestion.push_back("/A/" + current->getUrl());

src/search_renderer.cpp

@@ -1,152 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#include <cmath>
-
-#include "search_renderer.h"
-#include "searcher.h"
-#include "reader.h"
-#include "library.h"
-#include "name_mapper.h"
-
-#include <zim/search.h>
-
-#include <mustache.hpp>
-#include "kiwixlib-resources.h"
-
-
-namespace kiwix
-{
-
-/* Constructor */
-SearchRenderer::SearchRenderer(Searcher* searcher, NameMapper* mapper)
-    : mp_searcher(searcher),
-      mp_nameMapper(mapper),
-      protocolPrefix("zim://"),
-      searchProtocolPrefix("search://?")
-{}
-
-/* Destructor */
-SearchRenderer::~SearchRenderer() = default;
-
-void SearchRenderer::setSearchPattern(const std::string& pattern)
-{
-  this->searchPattern = pattern;
-}
-
-void SearchRenderer::setSearchContent(const std::string& name)
-{
-  this->searchContent = name;
-}
-
-void SearchRenderer::setProtocolPrefix(const std::string& prefix)
-{
-  this->protocolPrefix = prefix;
-}
-
-void SearchRenderer::setSearchProtocolPrefix(const std::string& prefix)
-{
-  this->searchProtocolPrefix = prefix;
-}
-
-std::string SearchRenderer::getHtml()
-{
-  kainjow::mustache::data results{kainjow::mustache::data::type::list};
-
-  mp_searcher->restart_search();
-  Result* p_result = NULL;
-  while ((p_result = mp_searcher->getNextResult())) {
-    kainjow::mustache::data result;
-    result.set("title", p_result->get_title());
-    result.set("url", p_result->get_url());
-    result.set("snippet", p_result->get_snippet());
-    auto readerIndex = p_result->get_readerIndex();
-    auto reader = mp_searcher->get_reader(readerIndex);
-    result.set("resultContentId", mp_nameMapper->getNameForId(reader->getId()));
-
-    if (p_result->get_wordCount() >= 0) {
-      result.set("wordCount", kiwix::beautifyInteger(p_result->get_wordCount()));
-    }
-
-    results.push_back(result);
-    delete p_result;
-  }
-
-  // pages
-  kainjow::mustache::data pages{kainjow::mustache::data::type::list};
-
-  auto resultStart = mp_searcher->getResultStart();
-  auto resultEnd = mp_searcher->getResultEnd();
-  auto resultCountPerPage = resultEnd - resultStart;
-  auto estimatedResultCount = mp_searcher->getEstimatedResultCount();
-  auto currentPage = 0U;
-  auto pageStart = 0U;
-  auto pageEnd = 0U;
-  auto lastPageStart = 0U;
-  if (resultCountPerPage) {
-    currentPage = resultStart/resultCountPerPage;
-    pageStart = currentPage > 4 ? currentPage-4 : 0;
-    pageEnd = currentPage + 5;
-    if (pageEnd > estimatedResultCount / resultCountPerPage) {
-      pageEnd = estimatedResultCount / resultCountPerPage;
-    }
-    if (estimatedResultCount > resultCountPerPage) {
-      lastPageStart = static_cast<int>(round(estimatedResultCount/resultCountPerPage)) * resultCountPerPage;
-    }
-  }
-
-  for (unsigned int i = pageStart; i < pageEnd; i++) {
-    kainjow::mustache::data page;
-    page.set("label", to_string(i + 1));
-    page.set("start", to_string(i * resultCountPerPage));
-    page.set("end", to_string((i + 1) * resultCountPerPage));
-
-    if (i == currentPage) {
-      page.set("selected", true);
-    }
-    pages.push_back(page);
-  }
-
-  std::string template_str = RESOURCE::templates::search_result_html;
-  kainjow::mustache::mustache tmpl(template_str);
-
-  kainjow::mustache::data allData;
-  allData.set("results", results);
-  allData.set("pages", pages);
-  allData.set("hasResults", estimatedResultCount != 0);
-  allData.set("hasPages", pageStart != pageEnd);
-  allData.set("count", kiwix::beautifyInteger(estimatedResultCount));
-  allData.set("searchPattern", kiwix::encodeDiples(this->searchPattern));
-  allData.set("searchPatternEncoded", urlEncode(this->searchPattern));
-  allData.set("resultStart", to_string(resultStart + 1));
-  allData.set("resultEnd", to_string(min(resultEnd, estimatedResultCount)));
-  allData.set("resultRange", to_string(resultCountPerPage));
-  allData.set("resultLastPageStart", to_string(lastPageStart));
-  allData.set("lastResult", to_string(estimatedResultCount));
-  allData.set("protocolPrefix", this->protocolPrefix);
-  allData.set("searchProtocolPrefix", this->searchProtocolPrefix);
-  allData.set("contentId", this->searchContent);
-
-  std::stringstream ss;
-  tmpl.render(allData, [&ss](const std::string& str) { ss << str; });
-  return ss.str();
-}
-
-}

src/searcher.cpp

@@ -22,12 +22,20 @@
 
 #include "searcher.h"
 #include "reader.h"
+#include "xapianSearcher.h"
 
 #include <zim/search.h>
 
-#include <mustache.hpp>
+#ifdef ENABLE_CTPP2
+#include <ctpp2/CDT.hpp>
+#include <ctpp2/CTPP2FileLogger.hpp>
+#include <ctpp2/CTPP2SimpleVM.hpp>
+#include "ctpp2/CTPP2VMStringLoader.hpp"
 #include "kiwixlib-resources.h"
 
+using namespace CTPP;
+#endif
+
 #define MAX_SEARCH_LEN 140
 
 namespace kiwix
@@ -53,24 +61,52 @@ class _Result : public Result
 
 struct SearcherInternal {
   const zim::Search* _search;
+  XapianSearcher* _xapianSearcher;
   zim::Search::iterator current_iterator;
 
-  SearcherInternal() : _search(NULL) {}
+  SearcherInternal() : _search(NULL), _xapianSearcher(NULL) {}
   ~SearcherInternal()
   {
     if (_search != NULL) {
       delete _search;
     }
+    if (_xapianSearcher != NULL) {
+      delete _xapianSearcher;
+    }
   }
 };
 
 /* Constructor */
-Searcher::Searcher()
+Searcher::Searcher(const string& xapianDirectoryPath,
+                   Reader* reader,
+                   const string& humanReadableName)
     : internal(new SearcherInternal()),
       searchPattern(""),
+      protocolPrefix("zim://"),
+      searchProtocolPrefix("search://?"),
+      resultCountPerPage(0),
       estimatedResultCount(0),
       resultStart(0),
-      resultEnd(0)
+      resultEnd(0),
+      contentHumanReadableId(humanReadableName)
+{
+  loadICUExternalTables();
+  if (!reader || !reader->hasFulltextIndex()) {
+    internal->_xapianSearcher = new XapianSearcher(xapianDirectoryPath, reader);
+  }
+  this->humanReaderNames.push_back(humanReadableName);
+}
+
+Searcher::Searcher(const std::string& humanReadableName)
+    : internal(new SearcherInternal()),
+      searchPattern(""),
+      protocolPrefix("zim://"),
+      searchProtocolPrefix("search://?"),
+      resultCountPerPage(0),
+      estimatedResultCount(0),
+      resultStart(0),
+      resultEnd(0),
+      contentHumanReadableId(humanReadableName)
 {
   loadICUExternalTables();
 }
@@ -81,21 +117,16 @@ Searcher::~Searcher()
   delete internal;
 }
 
-bool Searcher::add_reader(Reader* reader)
+bool Searcher::add_reader(Reader* reader, const std::string& humanReadableName)
 {
   if (!reader->hasFulltextIndex()) {
       return false;
   }
   this->readers.push_back(reader);
+  this->humanReaderNames.push_back(humanReadableName);
   return true;
 }
 
-
-Reader* Searcher::get_reader(int readerIndex)
-{
-  return readers.at(readerIndex);
-}
-
 /* Search strings in the database */
 void Searcher::search(std::string& search,
                       unsigned int resultStart,
@@ -108,27 +139,47 @@ void Searcher::search(std::string& search,
     cout << "Performing query `" << search << "'" << endl;
   }
 
-  this->searchPattern = search;
-  this->resultStart = resultStart;
-  this->resultEnd = resultEnd;
+  /* If resultEnd & resultStart inverted */
+  if (resultStart > resultEnd) {
+    resultEnd += resultStart;
+    resultStart = resultEnd - resultStart;
+    resultEnd -= resultStart;
+  }
+
   /* Try to find results */
   if (resultStart != resultEnd) {
-    /* Perform the search */
-    string unaccentedSearch = removeAccents(search);
-    std::vector<const zim::File*> zims;
-    for (auto current = this->readers.begin(); current != this->readers.end();
-         current++) {
-      if ( (*current)->hasFulltextIndex() ) {
-          zims.push_back((*current)->getZimFileHandler());
-      }
+    /* Avoid big researches */
+    this->resultCountPerPage = resultEnd - resultStart;
+    if (this->resultCountPerPage > MAX_SEARCH_LEN) {
+      resultEnd = resultStart + MAX_SEARCH_LEN;
+      this->resultCountPerPage = MAX_SEARCH_LEN;
+    }
+
+    /* Perform the search */
+    this->searchPattern = search;
+    this->resultStart = resultStart;
+    this->resultEnd = resultEnd;
+    string unaccentedSearch = removeAccents(search);
+    if (internal->_xapianSearcher) {
+      internal->_xapianSearcher->searchInIndex(
+          unaccentedSearch, resultStart, resultEnd, verbose);
+      this->estimatedResultCount
+          = internal->_xapianSearcher->results.get_matches_estimated();
+    } else {
+      std::vector<const zim::File*> zims;
+      for (auto current = this->readers.begin(); current != this->readers.end();
+           current++) {
+        if ( (*current)->hasFulltextIndex() ) {
+            zims.push_back((*current)->getZimFileHandler());
+        }
+      }
+      zim::Search* search = new zim::Search(zims);
+      search->set_query(unaccentedSearch);
+      search->set_range(resultStart, resultEnd);
+      internal->_search = search;
+      internal->current_iterator = internal->_search->begin();
+      this->estimatedResultCount = internal->_search->get_matches_estimated();
     }
-    zim::Search* search = new zim::Search(zims);
-    search->set_verbose(verbose);
-    search->set_query(unaccentedSearch);
-    search->set_range(resultStart, resultEnd);
-    internal->_search = search;
-    internal->current_iterator = internal->_search->begin();
-    this->estimatedResultCount = internal->_search->get_matches_estimated();
   }
 
   return;
@@ -146,6 +197,29 @@ void Searcher::geo_search(float latitude, float longitude, float distance,
     cout << "Performing geo query `" << distance << "&(" << latitude << ";" << longitude << ")'" << endl;
   }
 
+  /* If resultEnd & resultStart inverted */
+  if (resultStart > resultEnd) {
+    resultEnd += resultStart;
+    resultStart = resultEnd - resultStart;
+    resultEnd -= resultStart;
+  }
+
+  /* Try to find results */
+  if (resultStart == resultEnd) {
+    return;
+  }
+
+  if (internal->_xapianSearcher) {
+    return;
+  }
+
+  /* Avoid big researches */
+  this->resultCountPerPage = resultEnd - resultStart;
+  if (this->resultCountPerPage > MAX_SEARCH_LEN) {
+    resultEnd = resultStart + MAX_SEARCH_LEN;
+    this->resultCountPerPage = MAX_SEARCH_LEN;
+  }
+
   /* Perform the search */
   std::ostringstream oss;
   oss << "Articles located less than " << distance << " meters of " << latitude << ";" << longitude;
@@ -153,18 +227,12 @@ void Searcher::geo_search(float latitude, float longitude, float distance,
   this->resultStart = resultStart;
   this->resultEnd = resultEnd;
 
-  /* Try to find results */
-  if (resultStart == resultEnd) {
-    return;
-  }
-
   std::vector<const zim::File*> zims;
   for (auto current = this->readers.begin(); current != this->readers.end();
        current++) {
     zims.push_back((*current)->getZimFileHandler());
   }
   zim::Search* search = new zim::Search(zims);
-  search->set_verbose(verbose);
   search->set_query("");
   search->set_georange(latitude, longitude, distance);
   search->set_range(resultStart, resultEnd);
@@ -176,14 +244,18 @@ void Searcher::geo_search(float latitude, float longitude, float distance,
 
 void Searcher::restart_search()
 {
-  if (internal->_search) {
+  if (internal->_xapianSearcher) {
+    internal->_xapianSearcher->restart_search();
+  } else if (internal->_search) {
     internal->current_iterator = internal->_search->begin();
   }
 }
 
 Result* Searcher::getNextResult()
 {
-  if (internal->_search &&
+  if (internal->_xapianSearcher) {
+    return internal->_xapianSearcher->getNextResult();
+  } else if (internal->_search &&
              internal->current_iterator != internal->_search->end()) {
     Result* result = new _Result(internal->current_iterator);
     internal->current_iterator++;
@@ -200,32 +272,37 @@ void Searcher::reset()
   return;
 }
 
-void Searcher::suggestions(std::string& searchPattern, const bool verbose)
+void Searcher::suggestions(std::string& search, const bool verbose)
 {
   this->reset();
 
   if (verbose == true) {
-    cout << "Performing suggestion query `" << searchPattern << "`" << endl;
+    cout << "Performing suggestion query `" << search << "`" << endl;
   }
 
-  this->searchPattern = searchPattern;
+  this->searchPattern = search;
   this->resultStart = 0;
   this->resultEnd = 10;
-  string unaccentedSearch = removeAccents(searchPattern);
+  string unaccentedSearch = removeAccents(search);
 
-  std::vector<const zim::File*> zims;
-  for (auto current = this->readers.begin(); current != this->readers.end();
-       current++) {
-    zims.push_back((*current)->getZimFileHandler());
+  if (internal->_xapianSearcher) {
+    /* [TODO] Suggestion on a external database ?
+     * We do not support that. */
+    this->estimatedResultCount = 0;
+  } else {
+    std::vector<const zim::File*> zims;
+    for (auto current = this->readers.begin(); current != this->readers.end();
+         current++) {
+      zims.push_back((*current)->getZimFileHandler());
+    }
+    zim::Search* search = new zim::Search(zims);
+    search->set_query(unaccentedSearch);
+    search->set_range(resultStart, resultEnd);
+    search->set_suggestion_mode(true);
+    internal->_search = search;
+    internal->current_iterator = internal->_search->begin();
+    this->estimatedResultCount = internal->_search->get_matches_estimated();
   }
-  zim::Search* search = new zim::Search(zims);
-  search->set_verbose(verbose);
-  search->set_query(unaccentedSearch);
-  search->set_range(resultStart, resultEnd);
-  search->set_suggestion_mode(true);
-  internal->_search = search;
-  internal->current_iterator = internal->_search->begin();
-  this->estimatedResultCount = internal->_search->get_matches_estimated();
 }
 
 /* Return the result count estimation */
@@ -234,6 +311,18 @@ unsigned int Searcher::getEstimatedResultCount()
   return this->estimatedResultCount;
 }
 
+bool Searcher::setProtocolPrefix(const std::string prefix)
+{
+  this->protocolPrefix = prefix;
+  return true;
+}
+
+bool Searcher::setSearchProtocolPrefix(const std::string prefix)
+{
+  this->searchProtocolPrefix = prefix;
+  return true;
+}
+
 _Result::_Result(zim::Search::iterator& iterator)
     : iterator(iterator)
 {
@@ -274,6 +363,103 @@ int _Result::get_readerIndex()
 {
   return iterator.get_fileIndex();
 }
+#ifdef ENABLE_CTPP2
 
+string Searcher::getHtml()
+{
+  SimpleVM oSimpleVM(
+      1024, //iIMaxFunctions (default value)
+      4096, //iIMaxArgStackSize (default value)
+      4096, //iIMaxCodeStackSize (default value)
+      10240 * 2 //iIMaxSteps (default*2)
+  );
 
+  // Fill data
+  CDT oData;
+  CDT resultsCDT(CDT::ARRAY_VAL);
+
+  this->restart_search();
+  Result* p_result = NULL;
+  while ((p_result = this->getNextResult())) {
+    CDT result;
+    result["title"] = p_result->get_title();
+    result["url"] = p_result->get_url();
+    result["snippet"] = p_result->get_snippet();
+    result["contentId"] = humanReaderNames[p_result->get_readerIndex()];
+
+    if (p_result->get_size() >= 0) {
+      result["size"] = kiwix::beautifyInteger(p_result->get_size());
+    }
+
+    if (p_result->get_wordCount() >= 0) {
+      result["wordCount"] = kiwix::beautifyInteger(p_result->get_wordCount());
+    }
+
+    resultsCDT.PushBack(result);
+    delete p_result;
+  }
+  this->restart_search();
+  oData["results"] = resultsCDT;
+
+  // pages
+  CDT pagesCDT(CDT::ARRAY_VAL);
+
+  unsigned int pageStart
+      = this->resultStart / this->resultCountPerPage >= 5
+            ? this->resultStart / this->resultCountPerPage - 4
+            : 0;
+  unsigned int pageCount
+      = this->estimatedResultCount / this->resultCountPerPage + 1 - pageStart;
+
+  if (pageCount > 10) {
+    pageCount = 10;
+  } else if (pageCount == 1) {
+    pageCount = 0;
+  }
+
+  for (unsigned int i = pageStart; i < pageStart + pageCount; i++) {
+    CDT page;
+    page["label"] = i + 1;
+    page["start"] = i * this->resultCountPerPage;
+    page["end"] = (i + 1) * this->resultCountPerPage;
+
+    if (i * this->resultCountPerPage == this->resultStart) {
+      page["selected"] = true;
+    }
+
+    pagesCDT.PushBack(page);
+  }
+  oData["pages"] = pagesCDT;
+
+  oData["count"] = kiwix::beautifyInteger(this->estimatedResultCount);
+  oData["searchPattern"] = kiwix::encodeDiples(this->searchPattern);
+  oData["searchPatternEncoded"] = urlEncode(this->searchPattern);
+  oData["resultStart"] = this->resultStart + 1;
+  oData["resultEnd"] = (this->resultEnd > this->estimatedResultCount
+                            ? this->estimatedResultCount
+                            : this->resultEnd);
+  oData["resultRange"] = this->resultCountPerPage;
+  oData["resultLastPageStart"]
+      = this->estimatedResultCount > this->resultCountPerPage
+            ? std::round(this->estimatedResultCount / this->resultCountPerPage) * this->resultCountPerPage
+            : 0;
+  oData["protocolPrefix"] = this->protocolPrefix;
+  oData["searchProtocolPrefix"] = this->searchProtocolPrefix;
+  oData["contentId"] = this->contentHumanReadableId;
+
+  std::string template_ct2 = RESOURCE::results_ct2;
+  VMStringLoader oLoader(template_ct2.c_str(), template_ct2.size());
+
+  FileLogger oLogger(stderr);
+
+  // DEBUG only (write output to stdout)
+  // oSimpleVM.Run(oData, oLoader, stdout, oLogger);
+
+  std::string sResult;
+  oSimpleVM.Run(oData, oLoader, sResult, oLogger);
+
+  return sResult;
+}
+
+#endif
 }

src/server.cpp

@@ -1,899 +0,0 @@
-/*
- * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "server.h"
-
-#ifdef _WIN32
-# if !defined(__MINGW32__) && (_MSC_VER < 1600)
-#   include "stdint4win.h"
-# endif
-# include <winsock2.h>
-# include <ws2tcpip.h>
-# ifdef __GNUC__
-  // inet_pton is not declared in mingw, even if the function exists.
-  extern "C" {
-    WINSOCK_API_LINKAGE  INT WSAAPI inet_pton( INT Family, PCSTR pszAddrString, PVOID pAddrBuf);
-  }
-# endif
-  typedef UINT64 uint64_t;
-  typedef UINT16 uint16_t;
-#endif
-
-extern "C" {
-#include <microhttpd.h>
-}
-
-#include "tools/otherTools.h"
-#include "tools/pathTools.h"
-#include "tools/regexTools.h"
-#include "tools/stringTools.h"
-#include "library.h"
-#include "name_mapper.h"
-#include "entry.h"
-#include "searcher.h"
-#include "search_renderer.h"
-#include "opds_dumper.h"
-
-#include <zim/uuid.h>
-
-#include <mustache.hpp>
-
-#include <pthread.h>
-#include <atomic>
-#include <string>
-#include <vector>
-#include <chrono>
-#include "kiwixlib-resources.h"
-
-#ifndef _WIN32
-# include <arpa/inet.h>
-#endif
-
-#include "server/request_context.h"
-#include "server/response.h"
-
-#define MAX_SEARCH_LEN 140
-#define KIWIX_MIN_CONTENT_SIZE_TO_DEFLATE 100
-
-namespace kiwix {
-
-static IdNameMapper defaultNameMapper;
-
-static int staticHandlerCallback(void* cls,
-                                 struct MHD_Connection* connection,
-                                 const char* url,
-                                 const char* method,
-                                 const char* version,
-                                 const char* upload_data,
-                                 size_t* upload_data_size,
-                                 void** cont_cls);
-
-
-class InternalServer {
-  public:
-    InternalServer(Library* library,
-                   NameMapper* nameMapper,
-                   std::string addr,
-                   int port,
-                   std::string root,
-                   int nbThreads,
-                   bool verbose,
-                   bool withTaskbar,
-                   bool withLibraryButton);
-    virtual ~InternalServer() = default;
-
-    int handlerCallback(struct MHD_Connection* connection,
-                        const char* url,
-                        const char* method,
-                        const char* version,
-                        const char* upload_data,
-                        size_t* upload_data_size,
-                        void** cont_cls);
-    bool start();
-    void stop();
-
-  private:
-    Response handle_request(const RequestContext& request);
-    Response build_500(const std::string& msg);
-    Response build_404(const RequestContext& request, const std::string& zimName);
-    Response build_homepage(const RequestContext& request);
-    Response handle_skin(const RequestContext& request);
-    Response handle_catalog(const RequestContext& request);
-    Response handle_meta(const RequestContext& request);
-    Response handle_search(const RequestContext& request);
-    Response handle_suggest(const RequestContext& request);
-    Response handle_random(const RequestContext& request);
-    Response handle_content(const RequestContext& request);
-
-    kainjow::mustache::data get_default_data();
-    Response get_default_response();
-
-    std::string m_addr;
-    int m_port;
-    std::string m_root;
-    int m_nbThreads;
-    std::atomic_bool m_verbose;
-    bool m_withTaskbar;
-    bool m_withLibraryButton;
-    struct MHD_Daemon* mp_daemon;
-
-    Library* mp_library;
-    NameMapper* mp_nameMapper;
-};
-
-
-Server::Server(Library* library, NameMapper* nameMapper) :
-  mp_library(library),
-  mp_nameMapper(nameMapper),
-  mp_server(nullptr)
-{
-}
-
-Server::~Server() = default;
-
-bool Server::start() {
-  mp_server.reset(new InternalServer(
-    mp_library,
-    mp_nameMapper,
-    m_addr,
-    m_port,
-    m_root,
-    m_nbThreads,
-    m_verbose,
-    m_withTaskbar,
-    m_withLibraryButton));
-  return mp_server->start();
-}
-
-void Server::stop() {
-  mp_server->stop();
-  mp_server.reset(nullptr);
-}
-
-void Server::setRoot(const std::string& root)
-{
-  m_root = root;
-  if (m_root[0] != '/') {
-    m_root = "/" + m_root;
-  }
-  if (m_root.back() == '/') {
-    m_root.erase(m_root.size() - 1);
-  }
-}
-
-
-InternalServer::InternalServer(Library* library,
-                               NameMapper* nameMapper,
-                               std::string addr,
-                               int port,
-                               std::string root,
-                               int nbThreads,
-                               bool verbose,
-                               bool withTaskbar,
-                               bool withLibraryButton) :
-  m_addr(addr),
-  m_port(port),
-  m_root(root),
-  m_nbThreads(nbThreads),
-  m_verbose(verbose),
-  m_withTaskbar(withTaskbar),
-  m_withLibraryButton(withLibraryButton),
-  mp_daemon(nullptr),
-  mp_library(library),
-  mp_nameMapper(nameMapper ? nameMapper : &defaultNameMapper)
-{}
-
-bool InternalServer::start() {
-#ifdef _WIN32
-  int flags = MHD_USE_SELECT_INTERNALLY;
-#else
-  int flags = MHD_USE_POLL_INTERNALLY;
-#endif
-  if (m_verbose.load())
-    flags |= MHD_USE_DEBUG;
-
-
-  struct sockaddr_in sockAddr;
-  memset(&sockAddr, 0, sizeof(sockAddr));
-  sockAddr.sin_family = AF_INET;
-  sockAddr.sin_port = htons(m_port);
-  if (m_addr.empty()) {
-    if (0 != INADDR_ANY)
-      sockAddr.sin_addr.s_addr = htonl(INADDR_ANY);
-  } else {
-    if (inet_pton(AF_INET, m_addr.c_str(), &(sockAddr.sin_addr.s_addr)) == 0) {
-      std::cerr << "Ip address " << m_addr << "  is not a valid ip address" << std::endl;
-      return false;
-    }
-  }
-
-  mp_daemon = MHD_start_daemon(flags,
-                            m_port,
-                            NULL,
-                            NULL,
-                            &staticHandlerCallback,
-                            this,
-                            MHD_OPTION_SOCK_ADDR, &sockAddr,
-                            MHD_OPTION_THREAD_POOL_SIZE, m_nbThreads,
-                            MHD_OPTION_END);
-  if (mp_daemon == nullptr) {
-    std::cerr << "Unable to instantiate the HTTP daemon. The port " << m_port
-              << " is maybe already occupied or need more permissions to be open. "
-                 "Please try as root or with a port number higher or equal to 1024."
-              << std::endl;
-    return false;
-  }
-  return true;
-}
-
-void InternalServer::stop()
-{
-  MHD_stop_daemon(mp_daemon);
-}
-
-static int staticHandlerCallback(void* cls,
-                                 struct MHD_Connection* connection,
-                                 const char* url,
-                                 const char* method,
-                                 const char* version,
-                                 const char* upload_data,
-                                 size_t* upload_data_size,
-                                 void** cont_cls)
-{
-  InternalServer* _this = static_cast<InternalServer*>(cls);
-
-  return _this->handlerCallback(connection,
-                                url,
-                                method,
-                                version,
-                                upload_data,
-                                upload_data_size,
-                                cont_cls);
-}
-
-int InternalServer::handlerCallback(struct MHD_Connection* connection,
-                                    const char* url,
-                                    const char* method,
-                                    const char* version,
-                                    const char* upload_data,
-                                    size_t* upload_data_size,
-                                    void** cont_cls)
-{
-  auto start_time = std::chrono::steady_clock::now();
-  if (m_verbose.load() ) {
-    printf("======================\n");
-    printf("Requesting : \n");
-    printf("full_url  : %s\n", url);
-  }
-  RequestContext request(connection, m_root, url, method, version);
-
-  if (m_verbose.load() ) {
-    request.print_debug_info();
-  }
-  /* Unexpected method */
-  if (request.get_method() != RequestMethod::GET
-   && request.get_method() != RequestMethod::POST) {
-    printf("Reject request because of unhandled request method.\n");
-    printf("----------------------\n");
-    return MHD_NO;
-  }
-
-  auto response = handle_request(request);
-
-  if (response.getReturnCode() == MHD_HTTP_INTERNAL_SERVER_ERROR) {
-    printf("========== INTERNAL ERROR !! ============\n");
-    if (!m_verbose.load()) {
-      printf("Requesting : \n");
-      printf("full_url : %s\n", url);
-      request.print_debug_info();
-    }
-  }
-
-  auto ret = response.send(request, connection);
-  auto end_time = std::chrono::steady_clock::now();
-  auto time_span = std::chrono::duration_cast<std::chrono::duration<double>>(end_time - start_time);
-  if (m_verbose.load()) {
-    printf("Request time : %fs\n", time_span.count());
-    printf("----------------------\n");
-  }
-  return ret;
-}
-
-
-Response InternalServer::handle_request(const RequestContext& request)
-{
-  try {
-    if (! request.is_valid_url())
-      return build_404(request, "");
-
-    if (kiwix::startsWith(request.get_url(), "/skin/"))
-      return handle_skin(request);
-
-    if (startsWith(request.get_url(), "/catalog"))
-      return handle_catalog(request);
-
-    if (request.get_url() == "/meta")
-      return handle_meta(request);
-
-    if (request.get_url() == "/search")
-      return handle_search(request);
-
-    if (request.get_url() == "/suggest")
-     return handle_suggest(request);
-
-    if (request.get_url() == "/random")
-      return handle_random(request);
-
-    return handle_content(request);
-  } catch (std::exception& e) {
-    fprintf(stderr, "===== Unhandled error : %s\n", e.what());
-    return build_500(e.what());
-  } catch (...) {
-    fprintf(stderr, "===== Unhandled unknown error\n");
-    return build_500("Unknown error");
-  }
-}
-
-kainjow::mustache::data InternalServer::get_default_data()
-{
-  kainjow::mustache::data data;
-  data.set("root", m_root);
-  return data;
-}
-
-Response InternalServer::get_default_response()
-{
-  return Response(m_root, m_verbose.load(), m_withTaskbar, m_withLibraryButton);
-}
-
-
-Response InternalServer::build_404(const RequestContext& request,
-                                   const std::string& bookName)
-{
-  kainjow::mustache::data results;
-  results.set("url", request.get_full_url());
-
-  auto response = get_default_response();
-  response.set_template(RESOURCE::templates::_404_html, results);
-  response.set_mimeType("text/html");
-  response.set_code(MHD_HTTP_NOT_FOUND);
-  response.set_compress(true);
-  response.set_taskbar(bookName, "");
-
-  return response;
-}
-
-Response InternalServer::build_500(const std::string& msg)
-{
-  kainjow::mustache::data data;
-  data.set("error", msg);
-  Response response(m_root, true, false, false);
-  response.set_template(RESOURCE::templates::_500_html, data);
-  response.set_mimeType("text/html");
-  response.set_code(MHD_HTTP_INTERNAL_SERVER_ERROR);
-  return response;
-}
-
-Response InternalServer::build_homepage(const RequestContext& request)
-{
-  auto data = get_default_data();
-
-  kainjow::mustache::data books{kainjow::mustache::data::type::list};
-  for (auto& bookId: mp_library->filter(kiwix::Filter().local(true).valid(true))) {
-    auto& currentBook = mp_library->getBookById(bookId);
-
-    kainjow::mustache::data book;
-    book.set("name", mp_nameMapper->getNameForId(bookId));
-    book.set("title", currentBook.getTitle());
-    book.set("description", currentBook.getDescription());
-    book.set("articleCount", beautifyInteger(currentBook.getArticleCount()));
-    book.set("mediaCount", beautifyInteger(currentBook.getMediaCount()));
-    books.push_back(book);
-  }
-
-  data.set("books", books);
-
-  auto response = get_default_response();
-  response.set_template(RESOURCE::templates::index_html, data);
-  response.set_mimeType("text/html; charset=utf-8");
-  response.set_compress(true);
-  response.set_taskbar("", "");
-  return response;
-}
-
-Response InternalServer::handle_meta(const RequestContext& request)
-{
-  std::string bookName;
-  std::string bookId;
-  std::string meta_name;
-  std::shared_ptr<Reader> reader;
-  try {
-    bookName = request.get_argument("content");
-    bookId = mp_nameMapper->getIdForName(bookName);
-    meta_name = request.get_argument("name");
-    reader = mp_library->getReaderById(bookId);
-  } catch (const std::out_of_range& e) {
-    return build_404(request, bookName);
-  }
-
-  if (reader == nullptr) {
-    return build_404(request, bookName);
-  }
-
-  std::string content;
-  std::string mimeType = "text";
-
-  if (meta_name == "title") {
-    content = reader->getTitle();
-  } else if (meta_name == "description") {
-    content = reader->getDescription();
-  } else if (meta_name == "language") {
-    content = reader->getLanguage();
-  } else if (meta_name == "name") {
-    content = reader->getName();
-  } else if (meta_name == "tags") {
-    content = reader->getTags();
-  } else if (meta_name == "date") {
-    content = reader->getDate();
-  } else if (meta_name == "creator") {
-    content = reader->getCreator();
-  } else if (meta_name == "publisher") {
-    content = reader->getPublisher();
-  } else if (meta_name == "favicon") {
-    reader->getFavicon(content, mimeType);
-  } else {
-    return build_404(request, bookName);
-  }
-
-  auto response = get_default_response();
-  response.set_content(content);
-  response.set_mimeType(mimeType);
-  response.set_compress(false);
-  response.set_cache(true);
-  return response;
-}
-
-Response InternalServer::handle_suggest(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_suggest\n");
-  }
-
-  std::string content;
-  std::string mimeType;
-  unsigned int maxSuggestionCount = 10;
-  unsigned int suggestionCount = 0;
-  std::string suggestion;
-
-  std::string bookName;
-  std::string bookId;
-  std::string term;
-  std::shared_ptr<Reader> reader;
-  try {
-    bookName = request.get_argument("content");
-    bookId = mp_nameMapper->getIdForName(bookName);
-    term = request.get_argument("term");
-    reader = mp_library->getReaderById(bookId);
-  } catch (const std::out_of_range&) {
-    return build_404(request, bookName);
-  }
-
-  if (m_verbose.load()) {
-    printf("Searching suggestions for: \"%s\"\n", term.c_str());
-  }
-
-  kainjow::mustache::data results{kainjow::mustache::data::type::list};
-
-  bool first = true;
-  if (reader != nullptr) {
-    /* Get the suggestions */
-    reader->searchSuggestionsSmart(term, maxSuggestionCount);
-    while (reader->getNextSuggestion(suggestion)) {
-      kainjow::mustache::data result;
-      result.set("label", suggestion);
-      result.set("value", suggestion);
-      result.set("first", first);
-      first = false;
-      results.push_back(result);
-      suggestionCount++;
-    }
-  }
-
-  /* Propose the fulltext search if possible */
-  if (reader->hasFulltextIndex()) {
-    kainjow::mustache::data result;
-    result.set("label", "containing '" + term + "'...");
-    result.set("value", term + " ");
-    result.set("first", first);
-    results.push_back(result);
-  }
-
-  auto data = get_default_data();
-  data.set("suggestions", results);
-
-  auto response = get_default_response();
-  response.set_template(RESOURCE::templates::suggestion_json, data);
-  response.set_mimeType("application/json; charset=utf-8");
-  response.set_compress(true);
-  return response;
-}
-
-Response InternalServer::handle_skin(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_skin\n");
-  }
-
-  auto response = get_default_response();
-  auto resourceName = request.get_url().substr(1);
-  try {
-    response.set_content(getResource(resourceName));
-  } catch (const ResourceNotFound& e) {
-    return build_404(request, "");
-  }
-  response.set_mimeType(getMimeTypeForFile(resourceName));
-  response.set_compress(true);
-  response.set_cache(true);
-  return response;
-}
-
-Response InternalServer::handle_search(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_search\n");
-  }
-
-  std::string bookName;
-  std::string bookId;
-  try {
-    bookName = request.get_argument("content");
-    bookId = mp_nameMapper->getIdForName(bookName);
-  } catch (const std::out_of_range&) {}
-
-  std::string patternString;
-  try {
-    patternString = request.get_argument("pattern");
-  } catch (const std::out_of_range&) {}
-
-  /* Retrive geo search */
-  bool has_geo_query = false;
-  float latitude = 0;
-  float longitude = 0;
-  float distance = 0;
-  try {
-    latitude = request.get_argument<float>("latitude");
-    longitude = request.get_argument<float>("longitude");
-    distance = request.get_argument<float>("distance");
-    has_geo_query = true;
-  } catch(const std::out_of_range&) {}
-    catch(const std::invalid_argument&) {}
-
-  std::shared_ptr<Reader> reader(nullptr);
-  try {
-    reader = mp_library->getReaderById(bookId);
-  } catch (const std::out_of_range&) {}
-
-  /* Try first to load directly the article */
-  if (reader != nullptr && !patternString.empty()) {
-    std::string patternCorrespondingUrl;
-    auto variants = reader->getTitleVariants(patternString);
-    auto variantsItr = variants.begin();
-
-    while (patternCorrespondingUrl.empty() && variantsItr != variants.end()) {
-      try {
-        auto entry = reader->getEntryFromTitle(*variantsItr);
-        entry = entry.getFinalEntry();
-        patternCorrespondingUrl = entry.getPath();
-        break;
-      } catch(kiwix::NoEntry& e) {
-        variantsItr++;
-      }
-    }
-
-    /* If article found then redirect directly to it */
-    if (!patternCorrespondingUrl.empty()) {
-      auto response = get_default_response();
-      response.set_redirection(m_root + "/" + bookName + "/" + patternCorrespondingUrl);
-      return response;
-    }
-  }
-
-  /* Make the search */
-  auto response = get_default_response();
-  response.set_mimeType("text/html; charset=utf-8");
-  response.set_taskbar(bookName, reader ? reader->getTitle() : "");
-  response.set_compress(true);
-
-  if ( (!reader && !bookName.empty())
-    || (patternString.empty() && ! has_geo_query) ) {
-    auto data = get_default_data();
-    data.set("pattern", encodeDiples(patternString));
-    response.set_template(RESOURCE::templates::no_search_result_html, data);
-    response.set_code(MHD_HTTP_NOT_FOUND);
-    return response;
-  }
-
-  Searcher searcher;
-  if (reader) {
-    searcher.add_reader(reader.get());
-  } else {
-    for (auto& bookId: mp_library->filter(kiwix::Filter().local(true).valid(true))) {
-      auto currentReader = mp_library->getReaderById(bookId);
-      if (currentReader) {
-        searcher.add_reader(currentReader.get());
-      }
-    }
-  }
-
-  auto start = 0;
-  try {
-    start = request.get_argument<unsigned int>("start");
-  } catch (const std::exception&) {}
-  auto end = 25;
-  try {
-    end = request.get_argument<unsigned int>("end");
-  } catch (const std::exception&) {}
-  if (start>end) {
-    auto tmp = start;
-    start = end;
-    end = tmp;
-  }
-  if (end > start + MAX_SEARCH_LEN) {
-    end = start + MAX_SEARCH_LEN;
-  }
-
-  /* Get the results */
-  try {
-    if (patternString.empty()) {
-      searcher.geo_search(latitude, longitude, distance,
-                           start, end, m_verbose.load());
-    } else {
-      searcher.search(patternString,
-                       start, end, m_verbose.load());
-    }
-    SearchRenderer renderer(&searcher, mp_nameMapper);
-    renderer.setSearchPattern(patternString);
-    renderer.setSearchContent(bookName);
-    renderer.setProtocolPrefix(m_root + "/");
-    renderer.setSearchProtocolPrefix(m_root + "/search?");
-    response.set_content(renderer.getHtml());
-  } catch (const std::exception& e) {
-    std::cerr << e.what() << std::endl;
-  }
-  return response;
-}
-
-Response InternalServer::handle_random(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_random\n");
-  }
-
-  std::string bookName;
-  std::string bookId;
-  std::shared_ptr<Reader> reader;
-  try {
-    bookName = request.get_argument("content");
-    bookId = mp_nameMapper->getIdForName(bookName);
-    reader = mp_library->getReaderById(bookId);
-  } catch (const std::out_of_range&) {
-    return build_404(request, bookName);
-  }
-
-  if (reader == nullptr) {
-    return build_404(request, bookName);
-  }
-
-  try {
-    auto entry = reader->getRandomPage();
-    entry = entry.getFinalEntry();
-    auto response = get_default_response();
-    response.set_redirection(m_root + "/" + bookName + "/" + kiwix::urlEncode(entry.getPath()));
-    return response;
-  } catch(kiwix::NoEntry& e) {
-    return build_404(request, bookName);
-  }
-}
-
-Response InternalServer::handle_catalog(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_catalog");
-  }
-
-  std::string host;
-  std::string url;
-  try {
-    host = request.get_header("Host");
-    url  = request.get_url_part(1);
-  } catch (const std::out_of_range&) {
-    return build_404(request, "");
-  }
-
-  if (url != "searchdescription.xml" && url != "root.xml" && url != "search") {
-    return build_404(request, "");
-  }
-
-  auto response = get_default_response();
-  response.set_compress(true);
-  if (url == "searchdescription.xml") {
-    response.set_template(RESOURCE::opensearchdescription_xml, get_default_data());
-    response.set_mimeType("application/opensearchdescription+xml");
-    return response;
-  }
-
-  zim::Uuid uuid;
-  kiwix::OPDSDumper opdsDumper;
-  opdsDumper.setRootLocation(m_root);
-  opdsDumper.setSearchDescriptionUrl("catalog/searchdescription.xml");
-  opdsDumper.setId(kiwix::to_string(uuid));
-  opdsDumper.setLibrary(mp_library);
-  response.set_mimeType("application/atom+xml;profile=opds-catalog;kind=acquisition; charset=utf-8");
-  std::vector<std::string> bookIdsToDump;
-  if (url == "root.xml") {
-    opdsDumper.setTitle("All zims");
-    uuid = zim::Uuid::generate(host);
-    bookIdsToDump = mp_library->filter(kiwix::Filter().valid(true).local(true).remote(true));
-  } else if (url == "search") {
-    std::string query;
-    std::string language;
-    std::vector<std::string> tags;
-    std::vector<std::string> noTags;
-    size_t count(10);
-    size_t startIndex(0);
-    try {
-      query = request.get_argument("q");
-    } catch (const std::out_of_range&) {}
-    try {
-      language = request.get_argument("lang");
-    } catch (const std::out_of_range&) {}
-    try {
-      count = extractFromString<unsigned long>(request.get_argument("count"));
-    } catch (...) {}
-    try {
-      startIndex = extractFromString<unsigned long>(request.get_argument("start"));
-    } catch (...) {}
-    try {
-      tags = kiwix::split(request.get_argument("notag"), ";");
-    } catch (...) {}
-    try {
-      noTags = kiwix::split(request.get_argument("notag"), ";");
-    } catch (...) {}
-    opdsDumper.setTitle("Search result for " + query);
-    uuid = zim::Uuid::generate();
-    bookIdsToDump = mp_library->filter(
-      kiwix::Filter().valid(true).local(true).remote(true)
-        .query(query)
-        .lang(language)
-        .acceptTags(tags)
-        .rejectTags(noTags)
-      );
-    auto totalResults = bookIdsToDump.size();
-    bookIdsToDump.erase(bookIdsToDump.begin(), bookIdsToDump.begin()+startIndex);
-    if (count>0 && bookIdsToDump.size() > count) {
-      bookIdsToDump.resize(count);
-    }
-    opdsDumper.setOpenSearchInfo(totalResults, startIndex, bookIdsToDump.size());
-  }
-
-  response.set_content(opdsDumper.dumpOPDSFeed(bookIdsToDump));
-  return response;
-}
-
-Response InternalServer::handle_content(const RequestContext& request)
-{
-  if (m_verbose.load()) {
-    printf("** running handle_content\n");
-  }
-
-  std::string baseUrl;
-  std::string content;
-  std::string mimeType;
-
-  kiwix::Entry entry;
-
-  std::string bookName;
-  try {
-    bookName = request.get_url_part(0);
-  } catch (const std::out_of_range& e) {
-    return build_homepage(request);
-  }
-  if (bookName.empty())
-    return build_homepage(request);
-
-  std::string bookId;
-  std::shared_ptr<Reader> reader;
-  try {
-    bookId = mp_nameMapper->getIdForName(bookName);
-    reader = mp_library->getReaderById(bookId);
-  } catch (const std::out_of_range& e) {
-    return build_404(request, bookName);
-  }
-
-  if (reader == nullptr) {
-    return build_404(request, bookName);
-  }
-
-  auto urlStr = request.get_url().substr(bookName.size()+1);
-  if (urlStr[0] == '/') {
-    urlStr = urlStr.substr(1);
-  }
-
-  try {
-    entry = reader->getEntryFromPath(urlStr);
-    if (entry.isRedirect() || urlStr.empty()) {
-      // If urlStr is empty, we want to mainPage.
-      // We must do a redirection to the real page.
-      entry = entry.getFinalEntry();
-      auto response = get_default_response();
-      response.set_redirection(m_root + "/" + bookName + "/" +
-        kiwix::urlEncode(entry.getPath()));
-      return response;
-    }
-  } catch(kiwix::NoEntry& e) {
-    if (m_verbose.load())
-      printf("Failed to find %s\n", urlStr.c_str());
-
-    return build_404(request, bookName);
-  }
-
-  try {
-    mimeType = entry.getMimetype();
-  } catch (exception& e) {
-    mimeType = "application/octet-stream";
-  }
-
-  if (m_verbose.load()) {
-    printf("Found %s\n", urlStr.c_str());
-    printf("mimeType: %s\n", mimeType.c_str());
-  }
-
-  if (mimeType.find("text/") != string::npos
-      || mimeType.find("application/javascript") != string::npos
-      || mimeType.find("application/json") != string::npos) {
-    zim::Blob raw_content = entry.getBlob();
-    content = string(raw_content.data(), raw_content.size());
-    auto response = get_default_response();
-
-    if (mimeType.find("text/html") != string::npos)
-      response.set_taskbar(bookName, reader->getTitle());
-
-    response.set_mimeType(mimeType);
-    response.set_content(content);
-    response.set_compress(true);
-    response.set_cache(true);
-    return response;
-  } else {
-    int range_len;
-    if (request.get_range().second == -1) {
-       range_len = entry.getSize() - request.get_range().first;
-    } else {
-       range_len = request.get_range().second - request.get_range().first;
-    }
-    auto response = get_default_response();
-    response.set_entry(entry);
-    response.set_mimeType(mimeType);
-    response.set_range_first(request.get_range().first);
-    response.set_range_len(range_len);
-    response.set_cache(true);
-    return response;
-  }
-}
-
-}

src/server/request_context.cpp

@@ -1,211 +0,0 @@
-/*
- * Copyright 2009-2016 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright 2017 Matthieu Gautier<mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#include "request_context.h"
-#include <string.h>
-#include <stdexcept>
-#include <sstream>
-#include <cstdio>
-#include <atomic>
-
-namespace kiwix {
-
-static std::atomic_ullong s_requestIndex(0);
-
-RequestContext::RequestContext(struct MHD_Connection* connection,
-                               std::string rootLocation,
-                               const std::string& _url,
-                               const std::string& method,
-                               const std::string& version) :
-  full_url(_url),
-  url(_url),
-  valid_url(true),
-  version(version),
-  requestIndex(s_requestIndex++),
-  acceptEncodingDeflate(false),
-  accept_range(false),
-  range_pair(0, -1)
-{
-  if (method == "GET") {
-    this->method = RequestMethod::GET;
-  } else if (method == "HEAD") {
-    this->method = RequestMethod::HEAD;
-  } else if (method == "POST") {
-    this->method = RequestMethod::POST;
-  } else if (method == "PUT") {
-    this->method = RequestMethod::PUT;
-  } else if (method == "DELETE") {
-    this->method = RequestMethod::DELETE_;
-  } else if (method == "CONNECT") {
-    this->method = RequestMethod::CONNECT;
-  } else if (method == "OPTIONS") {
-    this->method = RequestMethod::OPTIONS;
-  } else if (method == "TRACE") {
-    this->method = RequestMethod::TRACE;
-  } else if (method == "PATCH") {
-    this->method = RequestMethod::PATCH;
-  } else {
-    this->method = RequestMethod::OTHER;
-  }
-
-  MHD_get_connection_values(connection, MHD_HEADER_KIND, &RequestContext::fill_header, this);
-  MHD_get_connection_values(connection, MHD_GET_ARGUMENT_KIND, &RequestContext::fill_argument, this);
-
-  valid_url = true;
-  if (rootLocation.empty()) {
-    // nothing special to handle.
-    url = full_url;
-  } else {
-    if (full_url == rootLocation) {
-      url = "/";
-    } else if (full_url.size() > rootLocation.size() &&
-               full_url.substr(0, rootLocation.size()+1) == rootLocation + "/") {
-      url = full_url.substr(rootLocation.size());
-    } else {
-      valid_url = false;
-    }
-  }
-
-  try {
-    acceptEncodingDeflate =
-        (get_header(MHD_HTTP_HEADER_ACCEPT_ENCODING).find("deflate") != std::string::npos);
-  } catch (const std::out_of_range&) {}
-
-  /*Check if range is requested. */
-  try {
-    auto range = get_header(MHD_HTTP_HEADER_RANGE);
-    int start = 0;
-    int end = -1;
-    std::istringstream iss(range);
-    char c;
-
-    iss >> start >> c;
-    if (iss.good() && c=='-') {
-      iss >> end;
-      if (iss.fail()) {
-        // Something went wrong will extracting.
-        end = -1;
-      }
-      if (iss.eof()) {
-        accept_range = true;
-        range_pair = std::pair<int, int>(start, end);
-      }
-    }
-  } catch (const std::out_of_range&) {}
-}
-
-RequestContext::~RequestContext()
-{}
-
-
-int RequestContext::fill_header(void *__this, enum MHD_ValueKind kind,
-                                 const char *key, const char *value)
-{
-  RequestContext *_this = static_cast<RequestContext*>(__this);
-  _this->headers[key] = value;
-  return MHD_YES;
-}
-
-int RequestContext::fill_argument(void *__this, enum MHD_ValueKind kind,
-                                   const char *key, const char* value)
-{
-  RequestContext *_this = static_cast<RequestContext*>(__this);
-  _this->arguments[key] = value == nullptr ? "" : value;
-  return MHD_YES;
-}
-
-void RequestContext::print_debug_info() const {
-  printf("method    : %s (%d)\n", method==RequestMethod::GET ? "GET" :
-                                  method==RequestMethod::POST ? "POST" :
-                                  "OTHER", (int)method);
-  printf("version   : %s\n", version.c_str());
-  printf("request#  : %lld\n", requestIndex);
-  printf("headers   :\n");
-  for (auto it=headers.begin(); it!=headers.end(); it++) {
-    printf(" - %s : '%s'\n", it->first.c_str(), it->second.c_str());
-  }
-  printf("arguments :\n");
-  for (auto it=arguments.begin(); it!=arguments.end(); it++) {
-    printf(" - %s : '%s'\n", it->first.c_str(), it->second.c_str());
-  }
-  printf("Parsed : \n");
-  printf("url   : %s\n", url.c_str());
-  printf("acceptEncodingDeflate : %d\n", acceptEncodingDeflate);
-  printf("has_range : %d\n", accept_range);
-  printf("is_valid_url : %d\n", valid_url);
-  printf(".............\n");
-}
-
-
-RequestMethod RequestContext::get_method() const {
-  return method;
-}
-
-std::string RequestContext::get_url() const {
-  return url;
-}
-
-std::string RequestContext::get_url_part(int number) const {
-  size_t start = 1;
-  while(true) {
-    auto found = url.find('/', start);
-    if (number == 0) {
-      if (found == std::string::npos) {
-        return url.substr(start);
-      } else {
-        return url.substr(start, found-start);
-      }
-    } else {
-      if (found == std::string::npos) {
-        throw std::out_of_range("No parts");
-      }
-      start = found + 1;
-      number -= 1;
-    }
-  }
-}
-
-std::string RequestContext::get_full_url() const {
-  return full_url;
-}
-
-bool RequestContext::is_valid_url() const {
-  return valid_url;
-}
-
-bool RequestContext::has_range() const {
-  return accept_range;
-}
-
-std::pair<int, int> RequestContext::get_range() const {
-  return range_pair;
-}
-
-template<>
-std::string RequestContext::get_argument(const std::string& name) const {
-  return arguments.at(name);
-}
-
-std::string RequestContext::get_header(const std::string& name) const {
-  return headers.at(name);
-}
-
-}

src/server/request_context.h

@@ -1,109 +0,0 @@
-/*
- * Copyright 2009-2016 Emmanuel Engelhart <kelson@kiwix.org>
- * Copyright 2017 Matthieu Gautier<mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#ifndef REQUEST_CONTEXT_H
-#define REQUEST_CONTEXT_H
-
-#include <string>
-#include <sstream>
-#include <map>
-#include <stdexcept>
-
-extern "C" {
-#include <microhttpd.h>
-}
-
-namespace kiwix {
-
-enum class RequestMethod {
-    GET,
-    HEAD,
-    POST,
-    PUT,
-    DELETE_,
-    CONNECT,
-    OPTIONS,
-    TRACE,
-    PATCH,
-    OTHER
-};
-
-class KeyError : public std::runtime_error {};
-class IndexError: public std::runtime_error {};
-
-
-class RequestContext {
-  public:
-    RequestContext(struct MHD_Connection* connection,
-                   std::string rootLocation,
-                   const std::string& url,
-                   const std::string& method,
-                   const std::string& version);
-    ~RequestContext();
-
-    void print_debug_info() const;
-
-    bool is_valid_url() const;
-
-    std::string get_header(const std::string& name) const;
-    template<typename T=std::string>
-    T get_argument(const std::string& name) const {
-        std::istringstream stream(arguments.at(name));
-        T v;
-        stream >> v;
-        return v;
-    }
-
-
-    RequestMethod get_method() const;
-    std::string get_url() const;
-    std::string get_url_part(int part) const;
-    std::string get_full_url() const;
-
-    bool has_range() const;
-    std::pair<int, int> get_range() const;
-
-    bool can_compress() const { return acceptEncodingDeflate; }
-
-  private:
-    std::string full_url;
-    std::string url;
-    bool valid_url;
-    RequestMethod method;
-    std::string version;
-    unsigned long long requestIndex;
-
-    bool acceptEncodingDeflate;
-
-    bool accept_range;
-    std::pair<int, int> range_pair;
-    std::map<std::string, std::string> headers;
-    std::map<std::string, std::string> arguments;
-
-    static int fill_header(void *, enum MHD_ValueKind, const char*, const char*);
-    static int fill_argument(void *, enum MHD_ValueKind, const char*, const char*);
-};
-
-template<> std::string RequestContext::get_argument(const std::string& name) const;
-
-}
-
-#endif //REQUEST_CONTEXT_H

src/server/response.cpp

@@ -1,250 +0,0 @@
-
-
-
-#include "response.h"
-#include "request_context.h"
-#include "kiwixlib-resources.h"
-
-#include "tools/regexTools.h"
-#include "tools/stringTools.h"
-
-#include "string.h"
-#include <mustache.hpp>
-#include <zlib.h>
-
-
-#define KIWIX_MIN_CONTENT_SIZE_TO_DEFLATE 100
-
-namespace kiwix {
-
-Response::Response(const std::string& root, bool verbose, bool withTaskbar, bool withLibraryButton)
-  : m_verbose(verbose),
-    m_root(root),
-    m_content(""),
-    m_mimeType(""),
-    m_returnCode(MHD_HTTP_OK),
-    m_withTaskbar(withTaskbar),
-    m_withLibraryButton(withLibraryButton),
-    m_useCache(false),
-    m_addTaskbar(false),
-    m_bookName(""),
-    m_startRange(0),
-    m_lenRange(0)
-{
-}
-
-
-static int print_key_value (void *cls, enum MHD_ValueKind kind,
-                            const char *key, const char *value)
-{
-  printf (" - %s: '%s'\n", key, value);
-  return MHD_YES;
-}
-
-
-struct RunningResponse {
-   kiwix::Entry entry;
-   int range_start;
-
-   RunningResponse(kiwix::Entry entry,
-                   int range_start) :
-     entry(entry),
-     range_start(range_start)
-   {}
-};
-
-static ssize_t callback_reader_from_entry(void* cls,
-                                  uint64_t pos,
-                                  char* buf,
-                                  size_t max)
-{
-  RunningResponse* response = static_cast<RunningResponse*>(cls);
-
-  size_t max_size_to_set = min<size_t>(
-    max,
-    response->entry.getSize() - pos - response->range_start);
-
-  if (max_size_to_set <= 0) {
-    return MHD_CONTENT_READER_END_WITH_ERROR;
-  }
-
-  zim::Blob blob = response->entry.getBlob(response->range_start+pos, max_size_to_set);
-  memcpy(buf, blob.data(), max_size_to_set);
-  return max_size_to_set;
-}
-
-static void callback_free_response(void* cls)
-{
-  RunningResponse* response = static_cast<RunningResponse*>(cls);
-  delete response;
-}
-
-
-
-void print_response_info(int retCode, MHD_Response* response)
-{
-  printf("Response :\n");
-  printf("httpResponseCode : %d\n", retCode);
-  printf("headers :\n");
-  MHD_get_response_headers(response, print_key_value, nullptr);
-}
-
-
-std::string render_template(const std::string& template_str, kainjow::mustache::data data)
-{
-  kainjow::mustache::mustache tmpl(template_str);
-  kainjow::mustache::data urlencode{kainjow::mustache::lambda2{
-                               [](const std::string& str,const kainjow::mustache::renderer& r) { return urlEncode(r(str), true); }}};
-  data.set("urlencoded", urlencode);
-  std::stringstream ss;
-  tmpl.render(data, [&ss](const std::string& str) { ss << str; });
-  return ss.str();
-}
-
-
-void Response::introduce_taskbar()
-{
-  if (! m_withTaskbar)
-    // Taskbar is globally disabled.
-    return;
-  kainjow::mustache::data data;
-  data.set("root", m_root);
-  data.set("content", m_bookName);
-  data.set("hascontent", !m_bookName.empty());
-  data.set("title", m_bookTitle);
-  data.set("withlibrarybutton", m_withLibraryButton);
-  auto head_content = render_template(RESOURCE::templates::head_part_html, data);
-  m_content = appendToFirstOccurence(
-    m_content,
-    "<head>",
-    head_content);
-
-  auto taskbar_part = render_template(RESOURCE::templates::taskbar_part_html, data);
-  m_content = appendToFirstOccurence(
-    m_content,
-    "<body[^>]*>",
-    taskbar_part);
-}
-
-
-
-int Response::send(const RequestContext& request, MHD_Connection* connection)
-{
-  MHD_Response* response = nullptr;
-  switch (m_mode) {
-    case ResponseMode::RAW_CONTENT : {
-      if (m_addTaskbar) {
-        introduce_taskbar();
-      }
-
-      bool shouldCompress = m_compress && request.can_compress();
-      shouldCompress &= m_mimeType.find("text/") != string::npos
-                     || m_mimeType.find("application/javascript") != string::npos
-                     || m_mimeType.find("application/json") != string::npos;
-
-      shouldCompress &= (m_content.size() > KIWIX_MIN_CONTENT_SIZE_TO_DEFLATE);
-
-      if (shouldCompress) {
-        std::vector<Bytef> compr_buffer(compressBound(m_content.size()));
-        uLongf comprLen = compr_buffer.capacity();
-        int err = compress(&compr_buffer[0],
-                           &comprLen,
-                           (const Bytef*)(m_content.data()),
-                           m_content.size());
-        if (err == Z_OK && comprLen > 2 && comprLen < (m_content.size() + 2)) {
-          /* /!\ Internet Explorer has a bug with deflate compression.
-             It can not handle the first two bytes (compression headers)
-             We need to chunk them off (move the content 2bytes)
-             It has no incidence on other browsers
-             See http://www.subbu.org/blog/2008/03/ie7-deflate-or-not and comments */
-          m_content = string((char*)&compr_buffer[2], comprLen - 2);
-        } else {
-          shouldCompress = false;
-        }
-      }
-
-      response = MHD_create_response_from_buffer(
-        m_content.size(), const_cast<char*>(m_content.data()), MHD_RESPMEM_MUST_COPY);
-
-      if (shouldCompress) {
-        MHD_add_response_header(
-            response, MHD_HTTP_HEADER_VARY, "Accept-Encoding");
-        MHD_add_response_header(
-            response, MHD_HTTP_HEADER_CONTENT_ENCODING, "deflate");
-      }
-      MHD_add_response_header(response, MHD_HTTP_HEADER_CONTENT_TYPE, m_mimeType.c_str());
-      break;
-    }
-
-    case ResponseMode::REDIRECTION : {
-      response = MHD_create_response_from_buffer(0, nullptr, MHD_RESPMEM_MUST_COPY);
-      MHD_add_response_header(response, MHD_HTTP_HEADER_LOCATION, m_content.c_str());
-      break;
-    }
-
-    case ResponseMode::ENTRY : {
-      response = MHD_create_response_from_callback(m_entry.getSize(),
-                                                   16384,
-                                                   callback_reader_from_entry,
-                                                   new RunningResponse(m_entry, m_startRange),
-                                                   callback_free_response);
-      MHD_add_response_header(response,
-        MHD_HTTP_HEADER_CONTENT_TYPE, m_mimeType.c_str());
-      MHD_add_response_header(response, MHD_HTTP_HEADER_ACCEPT_RANGES, "bytes");
-      std::ostringstream oss;
-      oss << "bytes " << m_startRange << "-" << m_startRange + m_lenRange - 1
-          << "/" << m_entry.getSize();
-
-      MHD_add_response_header(response,
-        MHD_HTTP_HEADER_CONTENT_RANGE, oss.str().c_str());
-
-      MHD_add_response_header(response,
-        MHD_HTTP_HEADER_CONTENT_LENGTH, kiwix::to_string(m_lenRange).c_str());
-      break;
-    }
-  }
-
-  MHD_add_response_header(response, "Access-Control-Allow-Origin", "*");
-  MHD_add_response_header(response, MHD_HTTP_HEADER_CACHE_CONTROL,
-    m_useCache ? "max-age=2723040, public" : "no-cache, no-store, must-revalidate");
-
-  if (m_returnCode == MHD_HTTP_OK && request.has_range())
-    m_returnCode = MHD_HTTP_PARTIAL_CONTENT;
-
-  if (m_verbose)
-    print_response_info(m_returnCode, response);
-
-  auto ret = MHD_queue_response(connection, m_returnCode, response);
-  MHD_destroy_response(response);
-  return ret;
-}
-
-void Response::set_template(const std::string& template_str, kainjow::mustache::data data) {
-  set_content(render_template(template_str, data));
-}
-
-void Response::set_content(const std::string& content) {
-  m_content = content;
-  m_mode = ResponseMode::RAW_CONTENT;
-}
-
-void Response::set_redirection(const std::string& url) {
-  m_content = url;
-  m_mode = ResponseMode::REDIRECTION;
-  m_returnCode = MHD_HTTP_FOUND;
-}
-
-void Response::set_entry(const Entry& entry) {
-  m_entry = entry;
-  m_mode = ResponseMode::ENTRY;
-}
-
-void Response::set_taskbar(const std::string& bookName, const std::string& bookTitle)
-{
-  m_addTaskbar = true;
-  m_bookName = bookName;
-  m_bookTitle = bookTitle;
-}
-
-
-}

src/server/response.h

@@ -1,89 +0,0 @@
-/*
- * Copyright 2019 Matthieu Gautier<mgautier@kymeria.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-
-#ifndef KIWIXLIB_SERVER_RESPONSE_H
-#define KIWIXLIB_SERVER_RESPONSE_H
-
-#include <string>
-
-#include <mustache.hpp>
-#include "entry.h"
-
-extern "C" {
-#include <microhttpd.h>
-}
-
-namespace kiwix {
-
-enum class ResponseMode {
-  RAW_CONTENT,
-  REDIRECTION,
-  ENTRY
-};
-
-class RequestContext;
-
-class Response {
-  public:
-    Response(const std::string& root, bool verbose, bool withTaskbar, bool withLibraryButton);
-    ~Response() = default;
-
-    int send(const RequestContext& request, MHD_Connection* connection);
-
-    void set_template(const std::string& template_str, kainjow::mustache::data data);
-    void set_content(const std::string& content);
-    void set_redirection(const std::string& url);
-    void set_entry(const Entry& entry);
-
-
-    void set_mimeType(const std::string& mimeType) { m_mimeType = mimeType; }
-    void set_code(int code) { m_returnCode = code; }
-    void set_cache(bool cache) { m_useCache = cache; }
-    void set_compress(bool compress) { m_compress = compress; }
-    void set_taskbar(const std::string& bookName, const std::string& bookTitle);
-    void set_range_first(uint64_t start) { m_startRange = start; }
-    void set_range_len(uint64_t len) { m_lenRange = len; }
-
-    int getReturnCode() { return m_returnCode; }
-
-    void introduce_taskbar();
-
-  private:
-    bool m_verbose;
-    ResponseMode m_mode;
-    std::string m_root;
-    std::string m_content;
-    Entry m_entry;
-    std::string m_mimeType;
-    int m_returnCode;
-    bool m_withTaskbar;
-    bool m_withLibraryButton;
-    bool m_useCache;
-    bool m_compress;
-    bool m_addTaskbar;
-    std::string m_bookName;
-    std::string m_bookTitle;
-    uint64_t m_startRange;
-    uint64_t m_lenRange;
-};
-
-}
-
-#endif //KIWIXLIB_SERVER_RESPONSE_H

src/subprocess_unix.cpp

@@ -46,7 +46,7 @@ void* UnixImpl::waitForPID(void* _self)
 #endif
 
   UnixImpl* self = static_cast<UnixImpl*>(_self);
-  waitpid(self->m_pid, NULL, 0);
+  waitpid(self->m_pid, NULL, WEXITED);
 
   pthread_mutex_lock(&self->m_mutex);
   self->m_running = false;
@@ -67,7 +67,7 @@ void UnixImpl::run(commandLine_t& commandLine)
       commandLine.push_back(NULL);
       if (execvp(binary, const_cast<char* const*>(commandLine.data()))) {
         perror("Cannot launch\n");
-        _exit(-1);
+        exit(-1);
       }
 
       break;

src/tools/networkTools.cpp

@@ -1,59 +0,0 @@
-/*
- * Copyright 2012 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include <tools/networkTools.h>
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#include <curl/curl.h>
-
-#include <sstream>
-#include <iostream>
-#include <stdexcept>
-
-
-size_t write_callback_to_iss(char* ptr, size_t size, size_t nmemb, void* userdata)
-{
-  auto str = static_cast<std::stringstream*>(userdata);
-  str->write(ptr, nmemb);
-  return nmemb;
-}
-
-std::string kiwix::download(const std::string& url) {
-  auto curl = curl_easy_init();
-  std::stringstream ss;
-  curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
-  curl_easy_setopt(curl, CURLOPT_HTTPGET, 1L);
-  curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, &write_callback_to_iss);
-  curl_easy_setopt(curl, CURLOPT_WRITEDATA, &ss);
-  auto res = curl_easy_perform(curl);
-  if (res != CURLE_OK) {
-    curl_easy_cleanup(curl);
-    throw std::runtime_error("Cannot perform request");
-  }
-  long response_code;
-  curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &response_code);
-  curl_easy_cleanup(curl);
-  if (response_code != 200) {
-    throw std::runtime_error("Invalid return code from server");
-  }
-  return ss.str();
-}

src/tools/otherTools.cpp

@@ -1,206 +0,0 @@
-/*
- * Copyright 2014 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "tools/otherTools.h"
-
-#ifdef _WIN32
-#include <windows.h>
-#else
-#include <unistd.h>
-#endif
-
-#include <map>
-#include <pugixml.hpp>
-
-
-static std::map<std::string, std::string> codeisomapping {
-{ "aa", "aar" },
-{ "af", "afr" },
-{ "ak", "aka" },
-{ "am", "amh" },
-{ "ar", "ara" },
-{ "as", "asm" },
-{ "az", "aze" },
-{ "ba", "bak" },
-{ "be", "bel" },
-{ "bg", "bul" },
-{ "bm", "bam" },
-{ "bn", "ben" },
-{ "bo", "bod" },
-{ "br", "bre" },
-{ "bs", "bos" },
-{ "ca", "cat" },
-{ "ce", "che" },
-{ "co", "cos" },
-{ "cs", "ces" },
-{ "cu", "chu" },
-{ "cv", "chv" },
-{ "cy", "cym" },
-{ "da", "dan" },
-{ "de", "deu" },
-{ "dv", "div" },
-{ "dz", "dzo" },
-{ "ee", "ewe" },
-{ "el", "ell" },
-{ "en", "eng" },
-{ "es", "spa" },
-{ "et", "est" },
-{ "eu", "eus" },
-{ "fa", "fas" },
-{ "ff", "ful" },
-{ "fi", "fin" },
-{ "fo", "fao" },
-{ "fr", "fra" },
-{ "fy", "fry" },
-{ "ga", "gle" },
-{ "gd", "gla" },
-{ "gl", "glg" },
-{ "gn", "grn" },
-{ "gu", "guj" },
-{ "gv", "glv" },
-{ "ha", "hau" },
-{ "he", "heb" },
-{ "hi", "hin" },
-{ "hr", "hrv" },
-{ "hu", "hun" },
-{ "hy", "hye" },
-{ "ia", "ina" },
-{ "id", "ind" },
-{ "ig", "ibo" },
-{ "is", "isl" },
-{ "it", "ita" },
-{ "iu", "iku" },
-{ "ja", "jpn" },
-{ "jv", "jav" },
-{ "ka", "kat" },
-{ "ki", "kik" },
-{ "kk", "kaz" },
-{ "kl", "kal" },
-{ "km", "khm" },
-{ "kn", "kan" },
-{ "ko", "kor" },
-{ "ks", "kas" },
-{ "ku", "kur" },
-{ "kw", "cor" },
-{ "ky", "kir" },
-{ "lb", "ltz" },
-{ "lg", "lug" },
-{ "ln", "lin" },
-{ "lo", "lao" },
-{ "lt", "lit" },
-{ "lv", "lav" },
-{ "mg", "mlg" },
-{ "mi", "mri" },
-{ "mi", "mri" },
-{ "mk", "mkd" },
-{ "ml", "mal" },
-{ "mn", "mon" },
-{ "mr", "mar" },
-{ "ms", "msa" },
-{ "mt", "mlt" },
-{ "my", "mya" },
-{ "nb", "nob" },
-{ "ne", "nep" },
-{ "nl", "nld" },
-{ "nn", "nno" },
-{ "no", "nor" },
-{ "ny", "nya" },
-{ "oc", "oci" },
-{ "om", "orm" },
-{ "or", "ori" },
-{ "os", "oss" },
-{ "pa", "pan" },
-{ "pl", "pol" },
-{ "ps", "pus" },
-{ "pt", "por" },
-{ "qu", "que" },
-{ "rm", "roh" },
-{ "rn", "run" },
-{ "ro", "ron" },
-{ "ru", "rus" },
-{ "rw", "kin" },
-{ "sa", "san" },
-{ "sd", "snd" },
-{ "se", "sme" },
-{ "sg", "sag" },
-{ "si", "sin" },
-{ "sk", "slk" },
-{ "sl", "slv" },
-{ "sn", "sna" },
-{ "so", "som" },
-{ "sq", "sqi" },
-{ "sr", "srp" },
-{ "ss", "ssw" },
-{ "st", "sot" },
-{ "sv", "swe" },
-{ "sw", "swa" },
-{ "ta", "tam" },
-{ "te", "tel" },
-{ "tg", "tgk" },
-{ "th", "tha" },
-{ "ti", "tir" },
-{ "tk", "tuk" },
-{ "tl", "tgl" },
-{ "tn", "tsn" },
-{ "to", "ton" },
-{ "tr", "tur" },
-{ "ts", "tso" },
-{ "tt", "tat" },
-{ "ug", "uig" },
-{ "uk", "ukr" },
-{ "ur", "urd" },
-{ "uz", "uzb" },
-{ "ve", "ven" },
-{ "vi", "vie" },
-{ "wa", "wln" },
-{ "wo", "wol" },
-{ "xh", "xho" },
-{ "yo", "yor" },
-{ "zh", "zho" },
-{ "zu", "zul" }
-};
-
-void kiwix::sleep(unsigned int milliseconds)
-{
-#ifdef _WIN32
-  Sleep(milliseconds);
-#else
-  usleep(1000 * milliseconds);
-#endif
-}
-
-
-struct XmlStringWriter: pugi::xml_writer
-{
-  std::string result;
-  virtual void write(const void* data, size_t size){
-    result.append(static_cast<const char*>(data), size);
-  }
-};
-
-std::string kiwix::nodeToString(const pugi::xml_node& node)
-{
-  XmlStringWriter writer;
-  node.print(writer, "  ");
-  return writer.result;
-}
-
-std::string kiwix::converta2toa3(const std::string& a2code){
-  return codeisomapping.at(a2code);
-}

src/tools/pathTools.cpp

@@ -1,437 +0,0 @@
-/*
- * Copyright 2011-2014 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU  General Public License as published by
- * the Free Software Foundation; either version 3 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "tools/pathTools.h"
-
-#ifdef __APPLE__
-#include <limits.h>
-#include <mach-o/dyld.h>
-#elif _WIN32
-#include <direct.h>
-#include <windows.h>
-#include "shlwapi.h"
-#define getcwd _getcwd  // stupid MSFT "deprecation" warning
-#endif
-
-#include "tools/stringTools.h"
-
-#include <string.h>
-#include <map>
-#include <vector>
-#include <sys/stat.h>
-#include <sstream>
-#include <fstream>
-#include <iomanip>
-#include <iostream>
-#include <algorithm>
-
-#ifdef _WIN32
-  #define SEPARATOR "\\"
-#else
-  #define SEPARATOR "/"
-#include <unistd.h>
-#endif
-
-#include <stdlib.h>
-
-#ifndef PATH_MAX
-#define PATH_MAX 1024
-#endif
-
-
-#ifdef _WIN32
-std::string WideToUtf8(const std::wstring& wstr)
-{
-  auto needed_size = WideCharToMultiByte(CP_UTF8, 0, wstr.data(), wstr.size(), NULL, 0, NULL, NULL);
-  std::string ret(needed_size, 0);
-  WideCharToMultiByte(CP_UTF8, 0, wstr.data(), wstr.size(), &ret[0], needed_size, NULL, NULL);
-  return ret;
-}
-
-std::wstring Utf8ToWide(const std::string& str)
-{
-  auto needed_size = MultiByteToWideChar(CP_UTF8, 0, str.data(), str.size(), NULL, 0);
-  std::wstring ret(needed_size, 0);
-  MultiByteToWideChar(CP_UTF8, 0, str.data(), str.size(), &ret[0], needed_size);
-  return ret;
-}
-#endif
-
-bool isRelativePath(const std::string& path)
-{
-#ifdef _WIN32
-  return path.empty() || path.substr(1, 2) == ":\\" ? false : true;
-#else
-  return path.empty() || path.substr(0, 1) == "/" ? false : true;
-#endif
-}
-
-std::vector<std::string> normalizeParts(std::vector<std::string> parts, bool absolute)
-{
-  std::vector<std::string> ret;
-#ifdef _WIN32
-  //Special case if we have a drive directory not at first.
-  //Starts from there.
-  auto it = find_if(parts.rbegin(), parts.rend(),
-                    [](const std::string& p) ->bool
-                      { return p.length() == 2 && p[1] == ':'; });
-  if (it != parts.rend()) {
-    parts.erase(parts.begin(), it.base()-1);
-  }
-#endif
-
-  size_t index = 0;
-  for (auto& part: parts) {
-    index++;
-    if (part == "..") {
-      if (absolute) {
-        // We try to remove as far as possible.
-        if (ret.size() > 1) {
-          ret.pop_back();
-        }
-      } else {
-        // We remove only if we can remove it.
-        // Else we add it.
-        if (!ret.empty() && ret.back() != "..") {
-          ret.pop_back();
-        } else {
-          ret.push_back("..");
-        }
-      }
-      continue;
-    }
-    if (part == "") {
-#ifndef _WIN32
-      if (ret.empty() && (absolute || index<parts.size())) {
-        ret.push_back("");
-      }
-#endif
-      continue;
-    }
-    if (part == ".") {
-      continue;
-    }
-    ret.push_back(part);
-  }
-#ifndef _WIN32
-  if (absolute && ret.size() == 1 && ret.back() == "") {
-    ret.push_back("");
-  }
-#endif
-  return ret;
-}
-
-std::string computeRelativePath(const std::string& path, const std::string& absolutePath)
-{
-  auto pathParts = normalizeParts(kiwix::split(path, SEPARATOR, false), false);
-  auto absolutePathParts = kiwix::split(absolutePath, SEPARATOR, false);
-
-  unsigned int commonCount = 0;
-  while (commonCount < pathParts.size()
-         && commonCount < absolutePathParts.size()
-         && pathParts[commonCount] == absolutePathParts[commonCount]) {
-      commonCount++;
-  }
-
-  std::vector<std::string> relativeParts;
-  for (unsigned int i = commonCount; i < pathParts.size(); i++) {
-    relativeParts.push_back("..");
-  }
-  for (unsigned int i = commonCount; i < absolutePathParts.size(); i++) {
-    relativeParts.push_back(absolutePathParts[i]);
-  }
-  auto ret = kiwix::join(normalizeParts(relativeParts, false), SEPARATOR);
-  return ret;
-}
-
-std::string computeAbsolutePath(const std::string& path, const std::string& relativePath)
-{
-  std::string absolutePath = path;
-  if (path.empty()) {
-    absolutePath = getCurrentDirectory();
-  }
-
-  auto absoluteParts = normalizeParts(kiwix::split(absolutePath, SEPARATOR, false), true);
-  auto relativeParts = kiwix::split(relativePath, SEPARATOR, false);
-
-  absoluteParts.insert(absoluteParts.end(), relativeParts.begin(), relativeParts.end());
-  auto ret = kiwix::join(normalizeParts(absoluteParts, true), SEPARATOR);
-  return ret;
-}
-
-std::string removeLastPathElement(const std::string& path)
-{
-  auto parts = normalizeParts(kiwix::split(path, SEPARATOR, false), false);
-  if (!parts.empty()) {
-    parts.pop_back();
-  }
-  auto ret = kiwix::join(parts, SEPARATOR);
-  return ret;
-}
-
-std::string appendToDirectory(const std::string& directoryPath, const std::string& filename)
-{
-  std::string newPath = directoryPath;
-  if (!directoryPath.empty() && directoryPath.back() != SEPARATOR[0]) {
-    newPath += SEPARATOR;
-  }
-  newPath += filename;
-  return newPath;
-}
-
-std::string getLastPathElement(const std::string& path)
-{
-  auto parts = normalizeParts(kiwix::split(path, SEPARATOR), false);
-  if (parts.empty()) {
-    return "";
-  }
-  auto ret = parts.back();
-  return ret;
-}
-
-unsigned int getFileSize(const std::string& path)
-{
-#ifdef _WIN32
-  struct _stat filestatus;
-  _stat(path.c_str(), &filestatus);
-#else
-  struct stat filestatus;
-  stat(path.c_str(), &filestatus);
-#endif
-
-  return filestatus.st_size / 1024;
-}
-
-std::string getFileSizeAsString(const std::string& path)
-{
-  std::ostringstream convert;
-  convert << getFileSize(path);
-  return convert.str();
-}
-
-std::string getFileContent(const std::string& path)
-{
-  std::ifstream f(path, std::ios::in|std::ios::ate);
-  std::string content;
-  if (f.is_open()) {
-    auto size = f.tellg();
-    content.reserve(size);
-    f.seekg(0, std::ios::beg);
-    content.assign((std::istreambuf_iterator<char>(f)),
-                    std::istreambuf_iterator<char>());
-  }
-  return content;
-}
-
-bool fileExists(const std::string& path)
-{
-#ifdef _WIN32
-  return PathFileExistsW(Utf8ToWide(path).c_str());
-#else
-  bool flag = false;
-  std::fstream fin;
-  fin.open(path.c_str(), std::ios::in);
-  if (fin.is_open()) {
-    flag = true;
-  }
-  fin.close();
-  return flag;
-#endif
-}
-
-bool makeDirectory(const std::string& path)
-{
-#ifdef _WIN32
-  int status = _wmkdir(Utf8ToWide(path).c_str());
-#else
-  int status = mkdir(path.c_str(), S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
-#endif
-  return status == 0;
-}
-
-std::string makeTmpDirectory()
-{
-#ifdef _WIN32
-  wchar_t cbase[MAX_PATH];
-  wchar_t ctmp[MAX_PATH];
-  GetTempPathW(MAX_PATH-14, cbase);
-  // This create a file for us, ensure it is unique.
-  // So we need to delete it and create the directory using the same name.
-  GetTempFileNameW(cbase, L"kiwix", 0, ctmp);
-  DeleteFileW(ctmp);
-  _wmkdir(ctmp);
-  return WideToUtf8(ctmp);
-#else
-  char _template_array[] = {"/tmp/kiwix-lib_XXXXXX"};
-  std::string dir = mkdtemp(_template_array);
-  return dir;
-#endif
-}
-
-/* Try to create a link and if does not work then make a copy */
-bool copyFile(const std::string& sourcePath, const std::string& destPath)
-{
-  try {
-#ifndef _WIN32
-    if (link(sourcePath.c_str(), destPath.c_str()) != 0) {
-#endif
-      std::ifstream infile(sourcePath.c_str(), std::ios_base::binary);
-      std::ofstream outfile(destPath.c_str(), std::ios_base::binary);
-      outfile << infile.rdbuf();
-#ifndef _WIN32
-    }
-#endif
-  } catch (std::exception& e) {
-    std::cerr << e.what() << std::endl;
-    return false;
-  }
-
-  return true;
-}
-
-std::string getExecutablePath(bool realPathOnly)
-{
-  if (!realPathOnly) {
-    char* cAppImage = ::getenv("APPIMAGE");
-    if (cAppImage) {
-      char* cArgv0 = ::getenv("ARGV0");
-      char* cOwd = ::getenv("OWD");
-      if (cArgv0 && cOwd) {
-        auto ret = appendToDirectory(cOwd, cArgv0);
-        return ret;
-      }
-    }
-  }
-
-#ifdef _WIN32
-  std::wstring binRootPath(PATH_MAX, 0);
-  GetModuleFileNameW(NULL, &binRootPath[0], PATH_MAX);
-  std::string ret = WideToUtf8(binRootPath);
-  return ret;
-#elif __APPLE__
-  char binRootPath[PATH_MAX];
-  uint32_t max = (uint32_t)PATH_MAX;
-  _NSGetExecutablePath(binRootPath, &max);
-  return std::string(binRootPath);
-#else
-  char binRootPath[PATH_MAX];
-  ssize_t size = readlink("/proc/self/exe", binRootPath, PATH_MAX);
-  if (size != -1) {
-    return std::string(binRootPath, size);
-  }
-  return "";
-#endif
-}
-
-bool writeTextFile(const std::string& path, const std::string& content)
-{
-  std::ofstream file;
-  file.open(path.c_str());
-  file << content;
-  file.close();
-  return true;
-}
-
-std::string getCurrentDirectory()
-{
-#ifdef _WIN32
-  wchar_t* a_cwd = _wgetcwd(NULL, 0);
-  std::string ret = WideToUtf8(a_cwd);
-  free(a_cwd);
-#else
-  char* a_cwd = getcwd(NULL, 0);
-  std::string ret(a_cwd);
-  free(a_cwd);
-#endif
-  return ret;
-}
-
-std::string getDataDirectory()
-{
-#ifdef _WIN32
-  char* cDataDir = ::getenv("APPDATA");
-#else
-  char* cDataDir = ::getenv("KIWIX_DATA_DIR");
-#endif
-  std::string dataDir = cDataDir==nullptr ? "" : cDataDir;
-  if (!dataDir.empty()) {
-    return dataDir;
-  }
-#ifdef _WIN32
-  cDataDir = ::getenv("USERPROFILE");
-  dataDir = cDataDir==nullptr ? getCurrentDirectory() : cDataDir;
-#else
-  cDataDir = ::getenv("XDG_DATA_HOME");
-  dataDir = cDataDir==nullptr ? "" : cDataDir;
-  if (dataDir.empty()) {
-    cDataDir = ::getenv("HOME");
-    dataDir = cDataDir==nullptr ? getCurrentDirectory() : cDataDir;
-    dataDir = appendToDirectory(dataDir, ".local");
-    dataDir = appendToDirectory(dataDir, "share");
-  }
-#endif
-  auto ret = appendToDirectory(dataDir, "kiwix");
-  return ret;
-}
-
-static std::map<std::string, std::string> extMimeTypes = {
- { "html", "text/html"},
- { "htm", "text/html"},
- { "png", "image/png"},
- { "tiff", "image/tiff"},
- { "tif", "image/tiff"},
- { "jpeg", "image/jpeg"},
- { "jpg", "image/jpeg"},
- { "gif", "image/gif"},
- { "svg", "image/svg+xml"},
- { "txt", "text/plain"},
- { "xml", "text/xml"},
- { "pdf", "application/pdf"},
- { "ogg", "application/ogg"},
- { "js", "application/javascript"},
- { "css", "text/css"},
- { "otf", "application/vnd.ms-opentype"},
- { "ttf", "application/font-ttf"},
- { "woff", "application/font-woff"},
- { "vtt", "text/vtt"}
-};
-
-/* Try to get the mimeType from the file extension */
-std::string getMimeTypeForFile(const std::string& filename)
-{
-  std::string mimeType = "text/plain";
-  auto pos = filename.find_last_of(".");
-
-  if (pos != std::string::npos) {
-    std::string extension = filename.substr(pos + 1);
-
-    auto it = extMimeTypes.find(extension);
-    if (it != extMimeTypes.end()) {
-      mimeType = it->second;
-    } else {
-      it = extMimeTypes.find(kiwix::lcAll(extension));
-      if (it != extMimeTypes.end()) {
-        mimeType = it->second;
-      }
-    }
-  }
-
-  return mimeType;
-}
-

src/xapian/htmlparse.cc

@@ -0,0 +1,373 @@
+/* htmlparse.cc: simple HTML parser for omega indexer
+ *
+ * Copyright 1999,2000,2001 BrightStation PLC
+ * Copyright 2001 Ananova Ltd
+ * Copyright 2002,2006,2007,2008 Olly Betts
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
+ * USA
+ */
+
+// #include <config.h>
+
+#include "htmlparse.h"
+
+#include <xapian.h>
+
+// #include "utf8convert.h"
+
+#include <algorithm>
+
+#include <ctype.h>
+#include <cstring>
+#include <stdio.h>
+#include <stdlib.h>
+
+using namespace std;
+
+inline void
+lowercase_string(string &str)
+{
+    for (string::iterator i = str.begin(); i != str.end(); ++i) {
+	*i = tolower(static_cast<unsigned char>(*i));
+    }
+}
+
+map<string, unsigned int> HtmlParser::named_ents;
+
+inline static bool
+p_notdigit(char c)
+{
+    return !isdigit(static_cast<unsigned char>(c));
+}
+
+inline static bool
+p_notxdigit(char c)
+{
+    return !isxdigit(static_cast<unsigned char>(c));
+}
+
+inline static bool
+p_notalnum(char c)
+{
+    return !isalnum(static_cast<unsigned char>(c));
+}
+
+inline static bool
+p_notwhitespace(char c)
+{
+    return !isspace(static_cast<unsigned char>(c));
+}
+
+inline static bool
+p_nottag(char c)
+{
+    return !isalnum(static_cast<unsigned char>(c)) &&
+	c != '.' && c != '-' && c != ':'; // ':' for XML namespaces.
+}
+
+inline static bool
+p_whitespacegt(char c)
+{
+    return isspace(static_cast<unsigned char>(c)) || c == '>';
+}
+
+inline static bool
+p_whitespaceeqgt(char c)
+{
+    return isspace(static_cast<unsigned char>(c)) || c == '=' || c == '>';
+}
+
+bool
+HtmlParser::get_parameter(const string & param, string & value)
+{
+    map<string, string>::const_iterator i = parameters.find(param);
+    if (i == parameters.end()) return false;
+    value = i->second;
+    return true;
+}
+
+HtmlParser::HtmlParser()
+{
+    static const struct ent { const char *n; unsigned int v; } ents[] = {
+#include "namedentities.h"
+	{ NULL, 0 }
+    };
+    if (named_ents.empty()) {
+	const struct ent *i = ents;
+	while (i->n) {
+	    named_ents[string(i->n)] = i->v;
+	    ++i;
+	}
+    }
+}
+
+void
+HtmlParser::decode_entities(string &s)
+{
+    // We need a const_iterator version of s.end() - otherwise the
+    // find() and find_if() templates don't work...
+    string::const_iterator amp = s.begin(), s_end = s.end();
+    while ((amp = find(amp, s_end, '&')) != s_end) {
+	unsigned int val = 0;
+	string::const_iterator end, p = amp + 1;
+	if (p != s_end && *p == '#') {
+	    p++;
+	    if (p != s_end && (*p == 'x' || *p == 'X')) {
+		// hex
+		p++;
+		end = find_if(p, s_end, p_notxdigit);
+		sscanf(s.substr(p - s.begin(), end - p).c_str(), "%x", &val);
+	    } else {
+		// number
+		end = find_if(p, s_end, p_notdigit);
+		val = atoi(s.substr(p - s.begin(), end - p).c_str());
+	    }
+	} else {
+	    end = find_if(p, s_end, p_notalnum);
+	    string code = s.substr(p - s.begin(), end - p);
+	    map<string, unsigned int>::const_iterator i;
+	    i = named_ents.find(code);
+	    if (i != named_ents.end()) val = i->second;
+	}
+	if (end < s_end && *end == ';') end++;
+	if (val) {
+	    string::size_type amp_pos = amp - s.begin();
+	    if (val < 0x80) {
+		s.replace(amp_pos, end - amp, 1u, char(val));
+	    } else {
+		// Convert unicode value val to UTF-8.
+		char seq[4];
+		unsigned len = Xapian::Unicode::nonascii_to_utf8(val, seq);
+		s.replace(amp_pos, end - amp, seq, len);
+	    }
+	    s_end = s.end();
+	    // We've modified the string, so the iterators are no longer
+	    // valid...
+	    amp = s.begin() + amp_pos + 1;
+	} else {
+	    amp = end;
+	}
+    }
+}
+
+void
+HtmlParser::parse_html(const string &body)
+{
+    in_script = false;
+
+    parameters.clear();
+    string::const_iterator start = body.begin();
+
+    while (true) {
+	// Skip through until we find an HTML tag, a comment, or the end of
+	// document.  Ignore isolated occurrences of `<' which don't start
+	// a tag or comment.
+	string::const_iterator p = start;
+	while (true) {
+	    p = find(p, body.end(), '<');
+	    if (p == body.end()) break;
+	    unsigned char ch = *(p + 1);
+
+	    // Tag, closing tag, or comment (or SGML declaration).
+	    if ((!in_script && isalpha(ch)) || ch == '/' || ch == '!') break;
+
+	    if (ch == '?') {
+		// PHP code or XML declaration.
+		// XML declaration is only valid at the start of the first line.
+		// FIXME: need to deal with BOMs...
+		if (p != body.begin() || body.size() < 20) break;
+
+		// XML declaration looks something like this:
+		// <?xml version="1.0" encoding="UTF-8"?>
+		if (p[2] != 'x' || p[3] != 'm' || p[4] != 'l') break;
+		if (strchr(" \t\r\n", p[5]) == NULL) break;
+
+		string::const_iterator decl_end = find(p + 6, body.end(), '?');
+		if (decl_end == body.end()) break;
+
+		// Default charset for XML is UTF-8.
+		charset = "UTF-8";
+
+		string decl(p + 6, decl_end);
+		size_t enc = decl.find("encoding");
+		if (enc == string::npos) break;
+
+		enc = decl.find_first_not_of(" \t\r\n", enc + 8);
+		if (enc == string::npos || enc == decl.size()) break;
+
+		if (decl[enc] != '=') break;
+		
+		enc = decl.find_first_not_of(" \t\r\n", enc + 1);
+		if (enc == string::npos || enc == decl.size()) break;
+
+		if (decl[enc] != '"' && decl[enc] != '\'') break;
+
+		char quote = decl[enc++];
+		size_t enc_end = decl.find(quote, enc);
+
+		if (enc != string::npos)
+		    charset = decl.substr(enc, enc_end - enc);
+
+		break;
+	    }
+	    p++;
+	}
+
+	// Process text up to start of tag.
+	if (p > start) {
+	    string text = body.substr(start - body.begin(), p - start);
+	    // convert_to_utf8(text, charset);
+	    decode_entities(text);
+	    process_text(text);
+	}
+
+	if (p == body.end()) break;
+
+	start = p + 1;
+
+	if (start == body.end()) break;
+
+	if (*start == '!') {
+	    if (++start == body.end()) break;
+	    if (++start == body.end()) break;
+	    // comment or SGML declaration
+	    if (*(start - 1) == '-' && *start == '-') {
+		++start;
+		string::const_iterator close = find(start, body.end(), '>');
+		// An unterminated comment swallows rest of document
+		// (like Netscape, but unlike MSIE IIRC)
+		if (close == body.end()) break;
+
+		p = close;
+		// look for -->
+		while (p != body.end() && (*(p - 1) != '-' || *(p - 2) != '-'))
+		    p = find(p + 1, body.end(), '>');
+
+		if (p != body.end()) {
+		    // Check for htdig's "ignore this bit" comments.
+		    if (p - start == 15 && string(start, p - 2) == "htdig_noindex") {
+			string::size_type i;
+			i = body.find("<!--/htdig_noindex-->", p + 1 - body.begin());
+			if (i == string::npos) break;
+			start = body.begin() + i + 21;
+			continue;
+		    }
+		    // If we found --> skip to there.
+		    start = p;
+		} else {
+		    // Otherwise skip to the first > we found (as Netscape does).
+		    start = close;
+		}
+	    } else {
+		// just an SGML declaration, perhaps giving the DTD - ignore it
+		start = find(start - 1, body.end(), '>');
+		if (start == body.end()) break;
+	    }
+	    ++start;
+	} else if (*start == '?') {
+	    if (++start == body.end()) break;
+	    // PHP - swallow until ?> or EOF
+	    start = find(start + 1, body.end(), '>');
+
+	    // look for ?>
+	    while (start != body.end() && *(start - 1) != '?')
+		start = find(start + 1, body.end(), '>');
+
+	    // unterminated PHP swallows rest of document (rather arbitrarily
+	    // but it avoids polluting the database when things go wrong)
+	    if (start != body.end()) ++start;
+	} else {
+	    // opening or closing tag
+	    int closing = 0;
+
+	    if (*start == '/') {
+		closing = 1;
+		start = find_if(start + 1, body.end(), p_notwhitespace);
+	    }
+
+	    p = start;
+	    start = find_if(start, body.end(), p_nottag);
+	    string tag = body.substr(p - body.begin(), start - p);
+	    // convert tagname to lowercase
+	    lowercase_string(tag);
+
+	    if (closing) {
+		closing_tag(tag);
+		if (in_script && tag == "script") in_script = false;
+
+		/* ignore any bogus parameters on closing tags */
+		p = find(start, body.end(), '>');
+		if (p == body.end()) break;
+		start = p + 1;
+	    } else {
+		// FIXME: parse parameters lazily.
+		while (start < body.end() && *start != '>') {
+		    string name, value;
+
+		    p = find_if(start, body.end(), p_whitespaceeqgt);
+
+		    name.assign(body, start - body.begin(), p - start);
+
+		    p = find_if(p, body.end(), p_notwhitespace);
+
+		    start = p;
+		    if (start != body.end() && *start == '=') {
+			start = find_if(start + 1, body.end(), p_notwhitespace);
+
+			p = body.end();
+
+			int quote = *start;
+			if (quote == '"' || quote == '\'') {
+			    start++;
+			    p = find(start, body.end(), quote);
+			}
+
+			if (p == body.end()) {
+			    // unquoted or no closing quote
+			    p = find_if(start, body.end(), p_whitespacegt);
+			}
+			value.assign(body, start - body.begin(), p - start);
+			start = find_if(p, body.end(), p_notwhitespace);
+
+			if (!name.empty()) {
+			    // convert parameter name to lowercase
+			    lowercase_string(name);
+			    // in case of multiple entries, use the first
+			    // (as Netscape does)
+			    parameters.insert(make_pair(name, value));
+			}
+		    }
+		}
+#if 0
+		cout << "<" << tag;
+		map<string, string>::const_iterator x;
+		for (x = parameters.begin(); x != parameters.end(); x++) {
+		    cout << " " << x->first << "=\"" << x->second << "\"";
+		}
+		cout << ">\n";
+#endif
+		opening_tag(tag);
+		parameters.clear();
+
+		// In <script> tags we ignore opening tags to avoid problems
+		// with "a<b".
+		if (tag == "script") in_script = true;
+
+		if (start != body.end() && *start == '>') ++start;
+	    }
+	}
+    }
+}

src/xapian/htmlparse.h

@@ -0,0 +1,49 @@
+/* htmlparse.h: simple HTML parser for omega indexer
+ *
+ * Copyright 1999,2000,2001 BrightStation PLC
+ * Copyright 2002,2006,2008 Olly Betts
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
+ * USA
+ */
+
+#ifndef OMEGA_INCLUDED_HTMLPARSE_H
+#define OMEGA_INCLUDED_HTMLPARSE_H
+
+#include <string>
+#include <map>
+
+using std::string;
+using std::map;
+
+class HtmlParser {
+	map<string, string> parameters;
+    protected:
+	void decode_entities(string &s);
+	bool in_script;
+	string charset;
+	static map<string, unsigned int> named_ents;
+
+	bool get_parameter(const string & param, string & value);
+    public:
+	virtual void process_text(const string &/*text*/) { }
+	virtual void opening_tag(const string &/*tag*/) { }
+	virtual void closing_tag(const string &/*tag*/) { }
+	virtual void parse_html(const string &text);
+	HtmlParser();
+	virtual ~HtmlParser() { }
+};
+
+#endif // OMEGA_INCLUDED_HTMLPARSE_H

src/xapian/myhtmlparse.cc

@@ -0,0 +1,302 @@
+/* myhtmlparse.cc: subclass of HtmlParser for extracting text.
+ *
+ * Copyright 1999,2000,2001 BrightStation PLC
+ * Copyright 2002,2003,2004,2006,2007,2008 Olly Betts
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
+ * USA
+ */
+
+// #include <config.h>
+
+#include "myhtmlparse.h"
+
+// #include "utf8convert.h"
+
+#include <ctype.h>
+#include <string.h>
+
+inline void
+lowercase_string(string &str)
+{
+    for (string::iterator i = str.begin(); i != str.end(); ++i) {
+	*i = tolower(static_cast<unsigned char>(*i));
+    }
+}
+
+void
+MyHtmlParser::parse_html(const string &text, const string &charset_,
+			 bool charset_from_meta_)
+{
+    charset = charset_;
+    charset_from_meta = charset_from_meta_;
+    HtmlParser::parse_html(text);
+}
+
+void
+MyHtmlParser::process_text(const string &text)
+{
+    if (!text.empty() && !in_script_tag && !in_style_tag) {
+	string::size_type b = text.find_first_not_of(WHITESPACE);
+	if (b) pending_space = true;
+	while (b != string::npos) {
+	    if (pending_space && !dump.empty()) dump += ' ';
+	    string::size_type e = text.find_first_of(WHITESPACE, b);
+	    pending_space = (e != string::npos);
+	    if (!pending_space) {
+		dump.append(text.data() + b, text.size() - b);
+		return;
+	    }
+	    dump.append(text.data() + b, e - b);
+	    b = text.find_first_not_of(WHITESPACE, e + 1);
+	}
+    }
+}
+
+void
+MyHtmlParser::opening_tag(const string &tag)
+{
+    if (tag.empty()) return;
+    switch (tag[0]) {
+	case 'a':
+	    if (tag == "address") pending_space = true;
+	    break;
+	case 'b':
+	    if (tag == "body") {
+		dump.resize(0);
+		break;
+	    }
+	    if (tag == "blockquote" || tag == "br") pending_space = true;
+	    break;
+	case 'c':
+	    if (tag == "center") pending_space = true;
+	    break;
+	case 'd':
+	    if (tag == "dd" || tag == "dir" || tag == "div" || tag == "dl" ||
+		tag == "dt") pending_space = true;
+	    break;
+	case 'e':
+	    if (tag == "embed") pending_space = true;
+	    break;
+	case 'f':
+	    if (tag == "fieldset" || tag == "form") pending_space = true;
+	    break;
+	case 'h':
+	    // hr, and h1, ..., h6
+	    if (tag.length() == 2 && strchr("r123456", tag[1]))
+		pending_space = true;
+	    break;
+	case 'i':
+	    if (tag == "iframe" || tag == "img" || tag == "isindex" ||
+		tag == "input") pending_space = true;
+	    break;
+	case 'k':
+	    if (tag == "keygen") pending_space = true;
+	    break;
+	case 'l':
+	    if (tag == "legend" || tag == "li" || tag == "listing")
+		pending_space = true;
+	    break;
+	case 'm':
+	    if (tag == "meta") {
+		string content;
+		if (get_parameter("content", content)) {
+		    string name;
+		    if (get_parameter("name", name)) {
+			lowercase_string(name);
+			if (name == "description") {
+			    if (sample.empty()) {
+				swap(sample, content);
+				// convert_to_utf8(sample, charset);
+				decode_entities(sample);
+			    }
+			} else if (name == "keywords") {
+			    if (!keywords.empty()) keywords += ' ';
+			    // convert_to_utf8(content, charset);
+			    decode_entities(content);
+			    keywords += content;
+			} else if (name == "robots") {
+			    decode_entities(content);
+			    lowercase_string(content);
+			    if (content.find("none") != string::npos ||
+				content.find("noindex") != string::npos) {
+				indexing_allowed = false;
+				throw true;
+			    }
+			}
+			break;
+		    }
+		    // If the current charset came from a meta tag, don't
+		    // force reparsing again!
+		    if (charset_from_meta) break;
+		    string hdr;
+		    if (get_parameter("http-equiv", hdr)) {
+			lowercase_string(hdr);
+			if (hdr == "content-type") {
+			    lowercase_string(content);
+			    size_t start = content.find("charset=");
+			    if (start == string::npos) break;
+			    start += 8;
+			    if (start == content.size()) break;
+			    size_t end = start;
+			    if (content[start] != '"') {
+				while (end < content.size()) {
+				    unsigned char ch = content[end];
+				    if (ch <= 32 || ch >= 127 ||
+					strchr(";()<>@,:\\\"/[]?={}", ch))
+					break;
+				    ++end;
+				}
+			    } else {
+				++start;
+				++end;
+				while (end < content.size()) {
+				    unsigned char ch = content[end];
+				    if (ch == '"') break;
+				    if (ch == '\\') content.erase(end, 1);
+				    ++end;
+				}
+			    }
+			    string newcharset(content, start, end - start);
+			    if (charset != newcharset) {
+				throw newcharset;
+			    }
+			}
+		    }
+		    break;
+		}
+		if (charset_from_meta) break;
+		string newcharset;
+		if (get_parameter("charset", newcharset)) {
+		    // HTML5 added: <meta charset="...">
+		    lowercase_string(newcharset);
+		    if (charset != newcharset) {
+			throw newcharset;
+		    }
+		}
+		break;
+	    }
+	    if (tag == "marquee" || tag == "menu" || tag == "multicol")
+		pending_space = true;
+	    break;
+	case 'o':
+	    if (tag == "ol" || tag == "option") pending_space = true;
+	    break;
+	case 'p':
+	    if (tag == "p" || tag == "pre" || tag == "plaintext")
+		pending_space = true;
+	    break;
+	case 'q':
+	    if (tag == "q") pending_space = true;
+	    break;
+	case 's':
+	    if (tag == "style") {
+		in_style_tag = true;
+		break;
+	    }
+	    if (tag == "script") {
+		in_script_tag = true;
+		break;
+	    }
+	    if (tag == "select") pending_space = true;
+	    break;
+	case 't':
+	    if (tag == "table" || tag == "td" || tag == "textarea" ||
+		tag == "th") pending_space = true;
+	    break;
+	case 'u':
+	    if (tag == "ul") pending_space = true;
+	    break;
+	case 'x':
+	    if (tag == "xmp") pending_space = true;
+	    break;
+    }
+}
+
+void
+MyHtmlParser::closing_tag(const string &tag)
+{
+    if (tag.empty()) return;
+    switch (tag[0]) {
+	case 'a':
+	    if (tag == "address") pending_space = true;
+	    break;
+	case 'b':
+	    if (tag == "body") {
+		throw true;
+	    }
+	    if (tag == "blockquote" || tag == "br") pending_space = true;
+	    break;
+	case 'c':
+	    if (tag == "center") pending_space = true;
+	    break;
+	case 'd':
+	    if (tag == "dd" || tag == "dir" || tag == "div" || tag == "dl" ||
+		tag == "dt") pending_space = true;
+	    break;
+	case 'f':
+	    if (tag == "fieldset" || tag == "form") pending_space = true;
+	    break;
+	case 'h':
+	    // hr, and h1, ..., h6
+	    if (tag.length() == 2 && strchr("r123456", tag[1]))
+		pending_space = true;
+	    break;
+	case 'i':
+	    if (tag == "iframe") pending_space = true;
+	    break;
+	case 'l':
+	    if (tag == "legend" || tag == "li" || tag == "listing")
+		pending_space = true;
+	    break;
+	case 'm':
+	    if (tag == "marquee" || tag == "menu") pending_space = true;
+	    break;
+	case 'o':
+	    if (tag == "ol" || tag == "option") pending_space = true;
+	    break;
+	case 'p':
+	    if (tag == "p" || tag == "pre") pending_space = true;
+	    break;
+	case 'q':
+	    if (tag == "q") pending_space = true;
+	    break;
+	case 's':
+	    if (tag == "style") {
+		in_style_tag = false;
+		break;
+	    }
+	    if (tag == "script") {
+		in_script_tag = false;
+		break;
+	    }
+	    if (tag == "select") pending_space = true;
+	    break;
+	case 't':
+	    if (tag == "title") {
+		if (title.empty()) swap(title, dump);
+		break;
+	    }
+	    if (tag == "table" || tag == "td" || tag == "textarea" ||
+		tag == "th") pending_space = true;
+	    break;
+	case 'u':
+	    if (tag == "ul") pending_space = true;
+	    break;
+	case 'x':
+	    if (tag == "xmp") pending_space = true;
+	    break;
+    }
+}