Compare commits

..

1 Commits
9.2 ... 3.0.3

Author SHA1 Message Date
Matthieu Gautier
2ea701b6d6 New version 3.0.3 2018-11-12 12:25:16 +01:00
507 changed files with 157399 additions and 24312 deletions

View File

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

12
.github/FUNDING.yml vendored
View File

@@ -1,12 +0,0 @@
# These are supported funding model platforms
github: kiwix
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/

27
.github/move.yml vendored
View File

@@ -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

15
.github/stale.yml vendored
View File

@@ -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.

View File

@@ -1,152 +0,0 @@
name: CI
on: [push]
jobs:
Macos:
runs-on: macos-latest
steps:
- name: Checkout code
uses: actions/checkout@v1
- name: Setup python 3.5
uses: actions/setup-python@v1
with:
python-version: '3.5'
- name: Install packages
uses: mstksg/get-package@v1
with:
brew: gcovr pkg-config ninja
- name: Install python modules
run: pip3 install meson==0.49.2 pytest
- name: Install deps
shell: bash
run: |
ARCHIVE_NAME=deps2_osx_native_dyn_kiwix-lib.tar.xz
wget -O- http://tmp.kiwix.org/ci/${ARCHIVE_NAME} | tar -xJ -C $HOME
- name: Compile
shell: bash
run: |
export PKG_CONFIG_PATH=$HOME/BUILD_native_dyn/INSTALL/lib/pkgconfig
export CPPFLAGS="-I$HOME/BUILD_native_dyn/INSTALL/include"
meson . build --default-library=shared -Db_coverage=true
cd build
ninja
- name: Test
shell: bash
run: |
export LD_LIBRARY_PATH=$HOME/BUILD_native_dyn/INSTALL/lib:$HOME/BUILD_native_dyn/INSTALL/lib64
cd build
meson test --verbose
ninja coverage
env:
SKIP_BIG_MEMORY_TEST: 1
- name: Publish coverage
shell: bash
run: |
curl https://codecov.io/bash -o codecov.sh
bash codecov.sh -n osx_native_dyn -Z
rm codecov.sh
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
Linux:
strategy:
fail-fast: false
matrix:
target:
- native_static
- native_dyn
- android_arm
- android_arm64
- win32_static
- win32_dyn
include:
- target: native_static
image_variant: xenial
lib_postfix: '/x86_64-linux-gnu'
- target: native_dyn
image_variant: xenial
lib_postfix: '/x86_64-linux-gnu'
- target: android_arm
image_variant: xenial
lib_postfix: '/x86_64-linux-gnu'
- target: android_arm64
image_variant: xenial
lib_postfix: '/x86_64-linux-gnu'
- target: win32_static
image_variant: f31
lib_postfix: '64'
- target: win32_dyn
image_variant: f31
lib_postfix: '64'
env:
HOME: /home/runner
runs-on: ubuntu-latest
container:
image: "kiwix/kiwix-build_ci:${{matrix.image_variant}}-26"
steps:
- name: Extract branch name
shell: bash
run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
id: extract_branch
- name: Checkout code
shell: python
run: |
from subprocess import check_call
from os import environ
command = [
'git', 'clone',
'https://github.com/${{github.repository}}',
'--depth=1',
'--branch', '${{steps.extract_branch.outputs.branch}}'
]
check_call(command, cwd=environ['HOME'])
- name: Install deps
shell: bash
run: |
ARCHIVE_NAME=deps2_${OS_NAME}_${{matrix.target}}_kiwix-lib.tar.xz
wget -O- http://tmp.kiwix.org/ci/${ARCHIVE_NAME} | tar -xJ -C /home/runner
- name: Compile
shell: bash
run: |
meson --version
if [[ "${{matrix.target}}" =~ .*_dyn ]]; then
MESON_OPTION="--default-library=shared"
else
MESON_OPTION="--default-library=static"
fi
if [[ "${{matrix.target}}" =~ native_.* ]]; then
MESON_OPTION="$MESON_OPTION -Db_coverage=true"
else
MESON_OPTION="$MESON_OPTION --cross-file $HOME/BUILD_${{matrix.target}}/meson_cross_file.txt"
fi
if [[ "${{matrix.target}}" =~ android_.* ]]; then
MESON_OPTION="$MESON_OPTION -Dandroid=true"
fi
cd $HOME/kiwix-lib
meson . build ${MESON_OPTION}
cd build
ninja
env:
PKG_CONFIG_PATH: "/home/runner/BUILD_${{matrix.target}}/INSTALL/lib/pkgconfig:/home/runner/BUILD_${{matrix.target}}/INSTALL/lib${{matrix.lib_postfix}}/pkgconfig"
CPPFLAGS: "-I/home/runner/BUILD_${{matrix.target}}/INSTALL/include"
- name: Test
if: startsWith(matrix.target, 'native_')
shell: bash
run: |
cd $HOME/kiwix-lib/build
meson test --verbose
ninja coverage
env:
LD_LIBRARY_PATH: "/home/runner/BUILD_${{matrix.target}}/INSTALL/lib:/home/runner/BUILD_${{matrix.target}}/INSTALL/lib${{matrix.lib_postfix}}"
SKIP_BIG_MEMORY_TEST: 1
- name: Publish coverage
shell: bash
run: |
cd $HOME/kiwix-lib
curl https://codecov.io/bash -o codecov.sh
bash codecov.sh -n "${OS_NAME}_${{matrix.target}}" -Z
rm codecov.sh
if: startsWith(matrix.target, 'native_')
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

4
.gitignore vendored
View File

@@ -1,4 +0,0 @@
.idea/
*.swp
subprojects/googletest-release*
*.class

36
.travis.yml Normal file
View File

@@ -0,0 +1,36 @@
language: cpp
dist: trusty
sudo: false
cache: ccache
before_install:
- PATH=$PATH:$HOME/bin
install: travis/install_deps.sh
script: travis/compile.sh
env:
matrix:
- PLATFORM="native_static"
- PLATFORM="native_dyn"
- PLATFORM="win32_static"
- PLATFORM="win32_dyn"
- PLATFORM="android_arm"
- PLATFORM="android_arm64"
addons:
apt:
packages:
- cmake
- python3-pip
- libbz2-dev
- ccache
- zlib1g-dev
- uuid-dev
- libctpp2-dev
- ctpp2-utils
- libmicrohttpd-dev
- g++-mingw-w64-i686
- gcc-mingw-w64-i686
- gcc-mingw-w64-base
- mingw-w64-tools
matrix:
include:
- env: PLATFORM="native_dyn"
os: osx

View File

@@ -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

206
ChangeLog
View File

@@ -1,208 +1,3 @@
kiwix-lib 9.2
=============
* Add tests
* Refactoring server code.
* [SERVER] Add HEAD, Etag and If-None-Match support.
* [SERVER] Compress opds catalog answers.
kiwix-lib 9.1.2
===============
* Do not use the pathToSave if it is empty.
kiwix-lib 9.1.1
===============
* Fix the detection of the dataDirectory on windows.
kiwix-lib 9.1.0
===============
* [JAVA] Add a method to get the size of an article.
* Add a new method to the libray to get the book by path.
* Add a option to make the server blocks external link.
Links are intercepted by js an redirected to a "portail" page.
* [ODPS] Correctly handle book's articleCount and mediaCount.
kiwix-lib 9.0.1
===============
* [JAVA] Use a long to store the offset of an article in the zim file instead
of an int.
kiwix-lib 9.0.0
===============
* [OPDS] Correctly set the id of the OPDS stream.
* [OPDS] Do not try to filter the catalog if no filter field is given in the
request.
* [WINDOWS] Correctly convert path to wide chars when opening the library.xml
* [LIBRARY] Remove the function the read file using a native path.
All path must be utf8, no need to pass a native path along the utf8 path.
* [TEST] Fix tests using the main function of gtest instead of custom one.
* [CI] Move to github CI instead of Travis.
* The `Book::update` method always update the book's fields. Even if they are
not empty.
* [JAVA] Add wrapping around the library manager (opds parsing)
* [ARIA2] Add api option to start download with option (destination folder)
* [OPDS] Fixes about opds parsing, generation (missing attributes)
and requesting (server)
* Add methods on `Book` to get specific tag values (was on `Reader` only)
* Add flavour attribute to `Book`
* Fix opensearch description.
* Trust the given library.xml (by default) instead of reading the value from
the zim files.
* [OPDS] Be able to filter the content by name or size.
* [WINDOWS] Fix launching subcommand when there is spaces in the path.
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
===============
@@ -210,7 +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
===============

View File

@@ -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://github.com/kiwix/kiwix-lib/workflows/CI/badge.svg?query=branch%3Amaster)](https://github.com/kiwix/kiwix-lib/actions?query=branch%3Amaster)
[![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). Use Mustache version 3 only.
* 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
```
@@ -85,44 +85,37 @@ Meson. If you want statically linked libraries, you can add
Depending of you system, `ninja` may be called `ninja-build`.
Testing
-------
To run the automated tests:
```bash
cd build
meson test
```
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
@@ -130,7 +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
@@ -149,5 +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.

View File

@@ -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

View File

@@ -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
}

View File

@@ -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

View File

Binary file not shown.

View File

@@ -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

View File

@@ -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" "$@"

View File

@@ -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

View File

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

View File

@@ -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 '9.2' + (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")
}

View File

@@ -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

View File

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

View File

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

View File

@@ -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; }
@@ -60,15 +63,11 @@ class Book
const std::string& getUrl() const { return m_url; }
const std::string& getName() const { return m_name; }
const std::string& getTags() const { return m_tags; }
std::string getTagStr(const std::string& tagName) const;
bool getTagBool(const std::string& tagName) const;
const std::string& getFlavour() const { return m_flavour; }
const std::string& getOrigId() const { return m_origId; }
const uint64_t& getArticleCount() const { return m_articleCount; }
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; }
@@ -76,6 +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; }
@@ -84,7 +85,6 @@ class Book
void setDate(const std::string& date) { m_date = date; }
void setUrl(const std::string& url) { m_url = url; }
void setName(const std::string& name) { m_name = name; }
void setFlavour(const std::string& flavour) { m_flavour = flavour; }
void setTags(const std::string& tags) { m_tags = tags; }
void setOrigId(const std::string& origId) { m_origId = origId; }
void setArticleCount(uint64_t articleCount) { m_articleCount = articleCount; }
@@ -98,7 +98,9 @@ class Book
std::string m_id;
std::string m_downloadId;
std::string m_path;
bool m_pathValid = false;
bool m_pathValid;
std::string m_indexPath;
supportedIndexType m_indexType;
std::string m_title;
std::string m_description;
std::string m_language;
@@ -107,13 +109,12 @@ class Book
std::string m_date;
std::string m_url;
std::string m_name;
std::string m_flavour;
std::string m_tags;
std::string m_origId;
uint64_t m_articleCount = 0;
uint64_t m_mediaCount = 0;
bool m_readOnly = false;
uint64_t m_size = 0;
uint64_t m_articleCount;
uint64_t m_mediaCount;
bool m_readOnly;
uint64_t m_size;
mutable std::string m_favicon;
std::string m_faviconUrl;
std::string m_faviconMimeType;

View File

@@ -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

View File

@@ -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);
}

View File

@@ -1,6 +1,5 @@
/*
* Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
* Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
* 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
@@ -18,9 +17,22 @@
* MA 02110-1301, USA.
*/
package org.kiwix.kiwixlib;
#ifndef KIWIX_OTHERTOOLS_H
#define KIWIX_OTHERTOOLS_H
public class JNIICU
#ifdef _WIN32
#include <windows.h>
#else
#include <unistd.h>
#endif
#include <pugixml.hpp>
namespace kiwix
{
static public native void setDataDirectory(String icuDataDir);
void sleep(unsigned int milliseconds);
std::string nodeToString(pugi::xml_node node);
std::string converta2toa3(const std::string& a2code);
}
#endif

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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.

View File

@@ -25,7 +25,6 @@
#include <map>
#include <pthread.h>
#include <memory>
#include <stdexcept>
namespace kiwix
{
@@ -55,9 +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; }
@@ -93,7 +89,7 @@ class Downloader
void close();
Download* startDownload(const std::string& uri, const std::vector<std::pair<std::string, std::string>>& options = {});
Download* startDownload(const std::string& uri);
Download* getDownload(const std::string& did);
size_t getNbDownload() { return m_knownDownloads.size(); }

View File

@@ -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.
*

View File

@@ -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_

View File

@@ -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 };
@@ -46,80 +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;
std::string _name;
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);
Filter& name(std::string name);
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.
*
@@ -132,25 +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);
Book& getBookByPath(const std::string& path);
std::shared_ptr<Reader> getReaderById(const std::string& id);
/**
* Remove a book from the library.
@@ -164,18 +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.
*
@@ -206,13 +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.
*
@@ -228,27 +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.
*
@@ -271,18 +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;
};
}

View File

@@ -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

View File

@@ -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
{
@@ -69,12 +68,26 @@ class Manager
/**
* Read a `library.xml` and add book in the file to the library.
*
* @param path The (utf8) path to the `library.xml`.
* @param path The path to the `library.xml`.
* @param readOnly Set if the libray path could be overwritten latter with
* updated content.
* @return True if file has been properly parsed.
*/
bool readFile(const std::string& path, bool readOnly = true, bool trustLibrary = true);
bool readFile(const std::string& path, const bool readOnly = true);
/**
* Read a `library.xml` and add book in the file to the library.
*
* @param nativePath The path of the `library.xml`
* @param UTF8Path The utf8 version (?) of the path. Also the path where the
* library will be writen i readOnly is False.
* @param readOnly Set if the libray path could be overwritten latter with
* updated content.
* @return True if file has been properly parsed.
*/
bool readFile(const std::string& nativePath,
const std::string& UTF8Path,
const bool readOnly = true);
/**
* Load a library content store in the string.
@@ -87,8 +100,7 @@ class Manager
*/
bool readXml(const std::string& xml,
const bool readOnly = true,
const std::string& libraryPath = "",
bool trustLibrary = true);
const std::string& libraryPath = "");
/**
* Load a library content stored in a OPDS stream.
@@ -101,15 +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.
*
@@ -142,6 +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;
@@ -155,12 +207,13 @@ class Manager
bool readBookFromPath(const std::string& path, Book* book);
bool parseXmlDom(const pugi::xml_document& doc,
bool readOnly,
const std::string& libraryPath,
bool trustLibrary);
const bool readOnly,
const std::string& libraryPath);
bool parseOpdsDom(const pugi::xml_document& doc,
const std::string& urlHost);
private:
void checkAndCleanBookPaths(Book& book, const std::string& libraryPath);
};
}

View File

@@ -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

View File

@@ -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

View File

@@ -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"

View File

@@ -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.
*

View File

@@ -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

View File

@@ -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.
@@ -89,7 +126,7 @@ class Searcher
* @param resultEnd the end offset of the search results (used for pagination).
* @param verbose print some info on stdout if true.
*/
void search(const std::string& search,
void search(std::string& search,
unsigned int resultStart,
unsigned int resultEnd,
const bool verbose = false);
@@ -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();

View File

@@ -1,78 +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; }
void setBlockExternalLinks(bool blockExternalLinks)
{ m_blockExternalLinks = blockExternalLinks; }
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;
bool m_blockExternalLinks = false;
std::unique_ptr<InternalServer> mp_server;
};
}
#endif

View File

@@ -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

View File

@@ -1,46 +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.
*/
#ifndef KIWIX_OTHERTOOLS_H
#define KIWIX_OTHERTOOLS_H
#include <string>
#include <vector>
namespace pugi {
class xml_node;
}
namespace kiwix
{
void sleep(unsigned int milliseconds);
std::string nodeToString(const pugi::xml_node& node);
std::string converta2toa3(const std::string& a2code);
/*
* Convert all format tag string to new format
*/
std::vector<std::string> convertTags(const std::string& tags_str);
std::string getTagValueFromTagList(const std::vector<std::string>& tagList,
const std::string& tagName);
bool convertStrToBool(const std::string& value);
}
#endif

View File

@@ -1,48 +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>
#ifdef _WIN32
std::string WideToUtf8(const std::wstring& wstr);
std::wstring Utf8ToWide(const std::string& str);
#endif
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

98
include/xapianSearcher.h Normal file
View File

@@ -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

View File

@@ -1,33 +1,23 @@
project('kiwix-lib', 'cpp',
version : '9.2', # 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')
wrapper = get_option('wrapper')
static_deps = 'android' in wrapper or 'java' in wrapper or get_option('default_library') == 'static'
if 'android' in wrapper
static_deps = get_option('android') or get_option('default_library') == 'static'
if get_option('android')
extra_libs = ['-llog']
else
extra_libs = []
endif
if 'java' in wrapper
add_languages('java')
endif
thread_dep = dependency('threads')
libicu_dep = dependency('icu-i18n', static:static_deps)
libzim_dep = dependency('libzim', version : '>=6.1.1', 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
@@ -35,12 +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']
@@ -55,6 +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'))

View File

@@ -1,2 +1,4 @@
option('wrapper', type:'array', choices:['java', 'android'], value:[],
description: 'The wrapper to generate.')
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')

8
scripts/ctpp2c.sh Executable file
View File

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

View File

@@ -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.

View File

@@ -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'))

View File

@@ -19,7 +19,7 @@
*/
#include <jni.h>
#include "org_kiwix_kiwixlib_JNIICU.h"
#include "org_kiwix_kiwixlib_JNIKiwix.h"
#include <iostream>
#include <string>
@@ -28,14 +28,10 @@
#include "utils.h"
#if __ANDROID__
pthread_mutex_t globalLock = PTHREAD_RECURSIVE_MUTEX_INITIALIZER;
#else
pthread_mutex_t globalLock = PTHREAD_RECURSIVE_MUTEX_INITIALIZER_NP;
#endif
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);

View File

@@ -21,10 +21,10 @@
#include <jni.h>
#include <zim/file.h>
#include <exception>
#include <android/log.h>
#include "org_kiwix_kiwixlib_JNIKiwixReader.h"
#include "tools/base64.h"
#include "common/base64.h"
#include "reader.h"
#include "utils.h"
@@ -34,14 +34,14 @@ JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getNativeReader(
{
std::string cPath = jni2c(filename, env);
LOG("Attempting to create reader with: %s", cPath.c_str());
__android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create reader with: %s", cPath.c_str());
Lock l;
try {
kiwix::Reader* reader = new kiwix::Reader(cPath);
return reinterpret_cast<jlong>(new Handle<kiwix::Reader>(reader));
} catch (std::exception& e) {
LOG("Error opening ZIM file");
LOG(e.what());
__android_log_print(ANDROID_LOG_WARN, "kiwix", "Error opening ZIM file");
__android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
return 0;
}
}
@@ -64,8 +64,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getMainPage(JNIEnv* env, jobject obj)
std::string cUrl = READER->getMainPage().getPath();
url = c2jni(cUrl, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM main page");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM main page");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
url = NULL;
}
return url;
@@ -80,8 +80,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getId(JNIEnv* env, jobject obj)
std::string cId = READER->getId();
id = c2jni(cId, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM id");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM id");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
id = NULL;
}
@@ -91,14 +91,14 @@ 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();
size = c2jni(cSize, env);
size = c2jni(cSize);
} catch (std::exception& e) {
LOG("Unable to get ZIM file size");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM file size");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
}
return size;
@@ -113,8 +113,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getCreator(JNIEnv* env, jobject obj)
std::string cCreator = READER->getCreator();
creator = c2jni(cCreator, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM creator");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM creator");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
creator = NULL;
}
@@ -130,8 +130,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getPublisher(JNIEnv* env, jobject obj)
std::string cPublisher = READER->getPublisher();
publisher = c2jni(cPublisher, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM publish");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM publish");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
publisher = NULL;
}
return publisher;
@@ -146,8 +146,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getName(JNIEnv* env, jobject obj)
std::string cName = READER->getName();
name = c2jni(cName, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM name");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM name");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
name = NULL;
}
return name;
@@ -166,8 +166,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getFavicon(JNIEnv* env, jobject obj)
base64_encode(cContent),
env);
} catch (std::exception& e) {
LOG("Unable to get ZIM favicon");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM favicon");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
favicon = NULL;
}
return favicon;
@@ -182,8 +182,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getDate(JNIEnv* env, jobject obj)
std::string cDate = READER->getDate();
date = c2jni(cDate, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM date");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM date");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
date = NULL;
}
return date;
@@ -198,8 +198,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getLanguage(JNIEnv* env, jobject obj)
std::string cLanguage = READER->getLanguage();
language = c2jni(cLanguage, env);
} catch (std::exception& e) {
LOG("Unable to get ZIM language");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM language");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
language = NULL;
}
@@ -217,30 +217,15 @@ JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getMimeType(
auto cMimeType = entry.getMimetype();
mimeType = c2jni(cMimeType, env);
} catch (std::exception& e) {
LOG("Unable to get mime-type for url: %s", cUrl.c_str());
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get mime-type for url: %s", cUrl.c_str());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
mimeType = NULL;
}
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(std::string(), 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);
@@ -249,27 +234,24 @@ 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) {
LOG("Unable to get content for url: %s", cUrl.c_str());
LOG(e.what());
__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());
}
return data;
@@ -284,8 +266,8 @@ JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContentPa
/* Default values */
/* Retrieve the content */
std::string cUrl = jni2c(url, env);
unsigned int cOffset = jni2c(offset, env);
unsigned int cLen = jni2c(len, env);
unsigned int cOffset = jni2c(offset);
unsigned int cLen = jni2c(len);
try {
auto entry = READER->getEntryFromEncodedPath(cUrl);
entry = entry.getFinalEntry();
@@ -300,28 +282,12 @@ JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContentPa
setIntObjValue(cLen, sizeObj, env);
}
} catch (std::exception& e) {
LOG("Unable to get partial content for url: %s (%u : %u)", cUrl.c_str(), cOffset, cLen);
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get partial content for url: %s (%u : %u)", cUrl.c_str(), cOffset, cLen);
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
}
return data;
}
JNIEXPORT jlong JNICALL
Java_org_kiwix_kiwixlib_JNIKiwixReader_getArticleSize(
JNIEnv* env, jobject obj, jstring url)
{
std::string cUrl = jni2c(url, env);
try {
auto entry = READER->getEntryFromEncodedPath(cUrl);
entry = entry.getFinalEntry();
return c2jni(entry.getSize(), env);
} catch(std::exception& e) {
LOG("Unable to get size for url : %s", cUrl.c_str());
LOG(e.what());
}
return c2jni(0, env);
}
JNIEXPORT jobject JNICALL
Java_org_kiwix_kiwixlib_JNIKiwixReader_getDirectAccessInformation(
JNIEnv* env, jobject obj, jstring url)
@@ -338,8 +304,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getDirectAccessInformation(
auto part_info = entry.getDirectAccessInfo();
setPairObjValue(part_info.first, part_info.second, pair, env);
} catch (std::exception& e) {
LOG("Unable to get direct access info for url: %s", cUrl.c_str());
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get direct access info for url: %s", cUrl.c_str());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
}
return pair;
}
@@ -352,15 +318,15 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_searchSuggestions(JNIEnv* env,
{
jboolean retVal = JNI_FALSE;
std::string cPrefix = jni2c(prefix, env);
unsigned int cCount = jni2c(count, env);
unsigned int cCount = jni2c(count);
try {
if (READER->searchSuggestionsSmart(cPrefix, cCount)) {
retVal = JNI_TRUE;
}
} catch (std::exception& e) {
LOG("Unable to get search results for pattern: %s", cPrefix.c_str());
LOG(e.what());
__android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get search results for pattern: %s", cPrefix.c_str());
__android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
}
return retVal;
@@ -369,22 +335,19 @@ 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) {
LOG("Unable to get next suggestion");
LOG(e.what());
__android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get next suggestion");
__android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
}
return retVal;
@@ -404,8 +367,8 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getPageUrlFromTitle(JNIEnv* env,
setStringObjValue(entry.getPath(), urlObj, env);
return JNI_TRUE;
} catch (std::exception& e) {
LOG("Unable to get url for title %s: ", cTitle.c_str());
LOG(e.what());
__android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get url for title %s: ", cTitle.c_str());
__android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
}
return JNI_FALSE;
@@ -420,8 +383,8 @@ JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getTitle(
std::string cTitle = READER->getTitle();
title = c2jni(cTitle, env);
} catch (std::exception& e) {
LOG("Unable to get zim title");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get zim title");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
title = NULL;
}
return title;
@@ -436,42 +399,13 @@ Java_org_kiwix_kiwixlib_JNIKiwixReader_getDescription(JNIEnv* env, jobject obj)
std::string cDescription = READER->getDescription();
description = c2jni(cDescription, env);
} catch (std::exception& e) {
LOG("Unable to get zim description");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get zim description");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
description = NULL;
}
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, env);
} catch (std::exception& e) {
LOG("Unable to get article count.");
LOG(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, env);
} catch (std::exception& e) {
LOG("Unable to get media count.");
LOG(e.what());
}
return mediaCount;
}
JNIEXPORT jboolean JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getRandomPage(
JNIEnv* env, jobject obj, jobject urlObj)
{
@@ -483,8 +417,8 @@ JNIEXPORT jboolean JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getRandomPage(
setStringObjValue(cUrl, urlObj, env);
retVal = JNI_TRUE;
} catch (std::exception& e) {
LOG("Unable to get random page");
LOG(e.what());
__android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get random page");
__android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
}
return retVal;
}

View File

@@ -52,14 +52,14 @@ 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(
JNIEnv* env, jobject obj, jstring query, jint count)
{
std::string cquery = jni2c(query, env);
unsigned int ccount = jni2c(count, env);
unsigned int ccount = jni2c(count);
SEARCHER->search(cquery, 0, ccount);
}

26
src/android/meson.build Normal file
View File

@@ -0,0 +1,26 @@
kiwix_jni = custom_target('jni',
input: ['org/kiwix/kiwixlib/JNIKiwix.java',
'org/kiwix/kiwixlib/JNIKiwixReader.java',
'org/kiwix/kiwixlib/JNIKiwixSearcher.java',
'org/kiwix/kiwixlib/JNIKiwixInt.java',
'org/kiwix/kiwixlib/JNIKiwixString.java',
'org/kiwix/kiwixlib/JNIKiwixBool.java',
'org/kiwix/kiwixlib/JNIKiwixException.java',
'org/kiwix/kiwixlib/Pair.java'],
output: ['org_kiwix_kiwixlib_JNIKiwix.h',
'org_kiwix_kiwixlib_JNIKiwixReader.h',
'org_kiwix_kiwixlib_JNIKiwixSearcher.h',
'org_kiwix_kiwixlib_JNIKiwixSearcher_Result.h'],
command:['javac', '-d', '@OUTDIR@', '-h', '@OUTDIR@', '@INPUT@']
)
kiwix_sources += [
'android/kiwix.cpp',
'android/kiwixreader.cpp',
'android/kiwixsearcher.cpp',
kiwix_jni]
install_subdir('org', install_dir: 'kiwix-lib/java')
install_subdir('res', install_dir: 'kiwix-lib')
install_data('AndroidManifest.xml', install_dir: 'kiwix-lib')

View File

@@ -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);
}

View File

@@ -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);
@@ -82,16 +58,6 @@ public class JNIKiwixReader
int len,
JNIKiwixInt size);
/**
*
* Get the size of an article.
*
* @param url The url of the article.
* @return The size of the final (redirections are resolved) article (in byte).
* Return 0 if the article is not found.
*/
public native long getArticleSize(String url);
/**
* getDirectAccessInformation.
*
@@ -112,7 +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);

View File

@@ -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;
}
}

View File

@@ -22,5 +22,5 @@ package org.kiwix.kiwixlib;
public class Pair
{
public String filename;
public long offset;
public int offset;
}

150
src/android/utils.h Normal file
View File

@@ -0,0 +1,150 @@
/*
* 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.
*/
#ifndef _ANDROID_JNI_UTILS_H
#define _ANDROID_JNI_UTILS_H
#include <jni.h>
#include <pthread.h>
#include <string>
extern pthread_mutex_t globalLock;
inline jfieldID getHandleField(JNIEnv* env, jobject obj)
{
jclass c = env->GetObjectClass(obj);
// J is the type signature for long:
return env->GetFieldID(c, "nativeHandle", "J");
}
class Lock
{
protected:
pthread_mutex_t* lock;
public:
Lock() : lock(&globalLock) { pthread_mutex_lock(lock); }
Lock(const Lock&) = delete;
Lock& operator=(const Lock&) = delete;
Lock(Lock&& other) : lock(&globalLock) { other.lock = nullptr; }
virtual ~Lock()
{
if (lock) {
pthread_mutex_unlock(lock);
}
}
};
template <class T>
class LockedHandle;
template <class T>
class Handle
{
protected:
T* h;
public:
Handle(T* h) : h(h){};
// No destructor. This must and will be handled by dispose method.
static LockedHandle<T> getHandle(JNIEnv* env, jobject obj)
{
jlong handle = env->GetLongField(obj, getHandleField(env, obj));
return LockedHandle<T>(reinterpret_cast<Handle<T>*>(handle));
}
static void dispose(JNIEnv* env, jobject obj)
{
auto lHandle = getHandle(env, obj);
auto handle = lHandle.h;
delete handle->h;
delete handle;
}
friend class LockedHandle<T>;
};
template <class T>
struct LockedHandle : public Lock {
Handle<T>* h;
LockedHandle(Handle<T>* h) : h(h) {}
T* operator->() { return h->h; }
T* operator*() { return h->h; }
operator bool() const { return (h->h != nullptr); }
};
/* c2jni type conversion functions */
inline jboolean c2jni(const bool& val) { return val ? JNI_TRUE : JNI_FALSE; }
inline jstring c2jni(const std::string& val, JNIEnv* env)
{
return env->NewStringUTF(val.c_str());
}
inline jint c2jni(const int val) { return (jint)val; }
inline jint c2jni(const unsigned val) { return (unsigned)val; }
/* jni2c type conversion functions */
inline bool jni2c(const jboolean& val) { return val == JNI_TRUE; }
inline std::string jni2c(const jstring& val, JNIEnv* env)
{
const char* chars = env->GetStringUTFChars(val, 0);
std::string ret(chars);
env->ReleaseStringUTFChars(val, chars);
return ret;
}
inline int jni2c(const jint val) { return (int)val; }
/* Method to deal with variable passed by reference */
inline void setStringObjValue(const std::string& value,
const jobject obj,
JNIEnv* env)
{
jclass objClass = env->GetObjectClass(obj);
jfieldID objFid = env->GetFieldID(objClass, "value", "Ljava/lang/String;");
env->SetObjectField(obj, objFid, c2jni(value, env));
}
inline void setIntObjValue(const int value, const jobject obj, JNIEnv* env)
{
jclass objClass = env->GetObjectClass(obj);
jfieldID objFid = env->GetFieldID(objClass, "value", "I");
env->SetIntField(obj, objFid, value);
}
inline void setBoolObjValue(const bool value, const jobject obj, JNIEnv* env)
{
jclass objClass = env->GetObjectClass(obj);
jfieldID objFid = env->GetFieldID(objClass, "value", "Z");
env->SetIntField(obj, objFid, c2jni(value));
}
inline void setPairObjValue(const std::string& filename, const int offset,
const jobject obj, JNIEnv* env)
{
jclass objClass = env->GetObjectClass(obj);
jfieldID filenameFid = env->GetFieldID(objClass, "filename", "Ljava/lang/String;");
env->SetObjectField(obj, filenameFid, c2jni(filename, env));
jfieldID offsetFid = env->GetFieldID(objClass, "offset", "I");
env->SetIntField(obj, offsetFid, offset);
}
#endif // _ANDROID_JNI_UTILS_H

View File

@@ -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());
@@ -78,38 +61,23 @@ Aria2::Aria2():
callCmd.push_back("--max-concurrent-downloads=42");
callCmd.push_back("--rpc-max-request-size=6M");
callCmd.push_back("--file-allocation=none");
std::string launchCmd;
for (auto &cmd : callCmd) {
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) {
curl_easy_cleanup(mp_curl);
throw std::runtime_error("Cannot connect to aria2c rpc. Aria2c launch cmd : " + launchCmd);
throw std::runtime_error("Cannot connect to aria2c rpc");
}
}
@@ -160,16 +128,13 @@ std::string Aria2::doRequest(const MethodCall& methodCall)
throw std::runtime_error("Cannot perform request");
}
std::string Aria2::addUri(const std::vector<std::string>& uris, const std::vector<std::pair<std::string, std::string>>& options)
std::string Aria2::addUri(const std::vector<std::string>& uris)
{
MethodCall methodCall("aria2.addUri", m_secret);
auto uriParams = methodCall.newParamValue().getArray();
for (auto& uri : uris) {
uriParams.addValue().set(uri);
}
for (auto& option : options) {
methodCall.newParamValue().getStruct().addMember(option.first).getValue().set(option.second);
}
auto ret = doRequest(methodCall);
MethodResponse response(ret);
return response.getParamValue(0).getAsS();
@@ -193,6 +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;
@@ -207,27 +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);
@@ -241,25 +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

View File

@@ -34,15 +34,11 @@ class Aria2
virtual ~Aria2();
void close();
std::string addUri(const std::vector<std::string>& uri, const std::vector<std::pair<std::string, std::string>>& options = {});
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);
};
}; //end namespace kiwix

View File

@@ -20,19 +20,16 @@
#include "book.h"
#include "reader.h"
#include "tools/base64.h"
#include "tools/regexTools.h"
#include "tools/networkTools.h"
#include "tools/otherTools.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 */
@@ -45,54 +42,52 @@ bool Book::update(const kiwix::Book& other)
if (m_readOnly)
return false;
if (m_id != other.m_id)
return false;
m_readOnly = other.m_readOnly;
m_path = other.m_path;
m_pathValid = other.m_pathValid;
m_title = other.m_title;
m_description = other.m_description;
m_language = other.m_language;
m_creator = other.m_creator;
m_publisher = other.m_publisher;
m_date = other.m_date;
m_url = other.m_url;
m_name = other.m_name;
m_flavour = other.m_flavour;
m_tags = other.m_tags;
m_origId = other.m_origId;
m_articleCount = other.m_articleCount;
m_mediaCount = other.m_mediaCount;
m_size = other.m_size;
m_favicon = other.m_favicon;
m_faviconMimeType = other.m_faviconMimeType;
m_faviconUrl = other.m_faviconUrl;
m_downloadId = other.m_downloadId;
if (m_path.empty()) {
m_path = other.m_path;
}
if (m_url.empty()) {
m_url = other.m_url;
}
if (m_tags.empty()) {
m_tags = other.m_tags;
}
if (m_name.empty()) {
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;
}
return true;
}
void Book::update(const kiwix::Reader& reader)
{
m_path = reader.getZimFilePath();
m_pathValid = true;
m_id = reader.getId();
m_title = reader.getTitle();
m_description = reader.getDescription();
m_language = reader.getLanguage();
m_date = reader.getDate();
m_creator = reader.getCreator();
m_publisher = reader.getPublisher();
m_date = reader.getDate();
m_title = reader.getTitle();
m_name = reader.getName();
m_flavour = reader.getFlavour();
m_tags = reader.getTags();
m_origId = reader.getOrigId();
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);
}
@@ -106,24 +101,29 @@ void Book::updateFromXml(const pugi::xml_node& node, const std::string& baseDir)
path = computeAbsolutePath(baseDir, path);
}
m_path = path;
m_pathValid = fileExists(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");
m_description = ATTR("description");
m_language = ATTR("language");
m_date = ATTR("date");
m_creator = ATTR("creator");
m_publisher = ATTR("publisher");
m_date = ATTR("date");
m_url = ATTR("url");
m_name = ATTR("name");
m_flavour = ATTR("flavour");
m_tags = ATTR("tags");
m_origId = ATTR("origId");
m_articleCount = strtoull(ATTR("articleCount"), 0, 0);
m_mediaCount = strtoull(ATTR("mediaCount"), 0, 0);
m_size = strtoull(ATTR("size"), 0, 0) << 10;
m_favicon = base64_decode(ATTR("favicon"));
m_faviconMimeType = ATTR("faviconMimeType");
m_faviconUrl = ATTR("faviconUrl");
try {
m_downloadId = ATTR("downloadId");
} catch(...) {}
@@ -131,14 +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)
{
@@ -146,18 +138,11 @@ void Book::updateFromOpds(const pugi::xml_node& node, const std::string& urlHost
if (!m_id.compare(0, 9, "urn:uuid:")) {
m_id.erase(0, 9);
}
// No path on opds.
m_title = VALUE("title");
m_description = VALUE("summary");
m_description = VALUE("description");
m_language = VALUE("language");
m_date = VALUE("updated");
m_creator = node.child("author").child("name").child_value();
m_publisher = node.child("publisher").child("name").child_value();
m_date = fromOpdsDate(VALUE("updated"));
m_name = VALUE("name");
m_flavour = VALUE("flavour");
m_tags = VALUE("tags");
m_articleCount = strtoull(VALUE("articleCount"), 0, 0);
m_mediaCount = strtoull(VALUE("mediaCount"), 0, 0);
for(auto linkNode = node.child("link"); linkNode;
linkNode = linkNode.next_sibling("link")) {
std::string rel = linkNode.attribute("rel").value();
@@ -175,7 +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()) {
@@ -201,6 +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 {
@@ -212,12 +204,4 @@ const std::string& Book::getFavicon() const {
return m_favicon;
}
std::string Book::getTagStr(const std::string& tagName) const {
return getTagValueFromTagList(convertTags(m_tags), tagName);
}
bool Book::getTagBool(const std::string& tagName) const {
return convertStrToBool(getTagStr(tagName));
}
}

View File

@@ -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();
}
}

View File

@@ -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+/";

209
src/common/networkTools.cpp Normal file
View File

@@ -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();
}

326
src/common/otherTools.cpp Normal file
View File

@@ -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);
}

335
src/common/pathTools.cpp Normal file
View File

@@ -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");
}

View File

@@ -17,48 +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 <stdexcept>
#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();
}
@@ -67,9 +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;
@@ -78,13 +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);

View File

@@ -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());
}

View File

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

View File

@@ -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.

View File

@@ -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()
{
@@ -163,7 +122,7 @@ std::vector<std::string> Downloader::getDownloadIds() {
return ret;
}
Download* Downloader::startDownload(const std::string& uri, const std::vector<std::pair<std::string, std::string>>& options)
Download* Downloader::startDownload(const std::string& uri)
{
for (auto& p: m_knownDownloads) {
auto& d = p.second;
@@ -172,7 +131,7 @@ Download* Downloader::startDownload(const std::string& uri, const std::vector<st
return d.get();
}
std::vector<std::string> uris = {uri};
auto gid = mp_aria->addUri(uris, options);
auto gid = mp_aria->addUri(uris);
m_knownDownloads[gid] = std::unique_ptr<Download>(new Download(mp_aria, gid));
return m_knownDownloads[gid].get();
}
@@ -180,23 +139,14 @@ Download* Downloader::startDownload(const std::string& uri, const std::vector<st
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;
}
}

View File

@@ -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;
}

View File

@@ -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;
}
}

View File

@@ -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 */
@@ -48,74 +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);
}
Book& Library::getBookByPath(const std::string& path)
{
for(auto& it: m_books) {
auto& book = it.second;
if (book.getPath() == path)
return book;
}
std::ostringstream ss;
ss << "No book with path " << path << " in the library." << std::endl;
throw std::out_of_range(ss.str());
}
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)) {
@@ -125,18 +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()
@@ -144,7 +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()) {
@@ -163,7 +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()) {
@@ -182,7 +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()) {
@@ -196,26 +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);
}
@@ -228,104 +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,
@@ -334,208 +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),
NAME = FLAG(13),
};
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;
}
Filter& Filter::name(std::string name)
{
_name = name;
activeFilters |= NAME;
return *this;
}
#define ACTIVE(X) (activeFilters & (X))
#define FILTER(TAG, TEST) if (ACTIVE(TAG) && !(TEST)) { return false; }
bool Filter::accept(const Book& book) const
{
auto local = !book.getPath().empty();
FILTER(_LOCAL, local)
FILTER(_NOLOCAL, !local)
auto valid = book.isPathValid();
FILTER(_VALID, valid)
FILTER(_NOVALID, !valid)
auto remote = !book.getUrl().empty();
FILTER(_REMOTE, remote)
FILTER(_NOREMOTE, !remote)
FILTER(MAXSIZE, book.getSize() <= _maxSize)
FILTER(LANG, book.getLanguage() == _lang)
FILTER(_PUBLISHER, book.getPublisher() == _publisher)
FILTER(_CREATOR, book.getCreator() == _creator)
FILTER(NAME, book.getName() == _name)
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(QUERY)
&& !(matchRegex(book.getTitle(), "\\Q" + _query + "\\E")
|| matchRegex(book.getDescription(), "\\Q" + _query + "\\E")))
return false;
return true;
}
}

View File

@@ -1,142 +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, "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, "name", book.getName());
ADD_ATTR_NOT_EMPTY(entry_node, "flavour", book.getFlavour());
ADD_ATTR_NOT_EMPTY(entry_node, "tags", book.getTags());
ADD_ATTR_NOT_EMPTY(entry_node, "faviconMimeType", book.getFaviconMimeType());
ADD_ATTR_NOT_EMPTY(entry_node, "faviconUrl", book.getFaviconUrl());
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);
}
}

View File

@@ -19,8 +19,6 @@
#include "manager.h"
#include "tools/pathTools.h"
#include <pugixml.hpp>
namespace kiwix
@@ -48,9 +46,8 @@ Manager::~Manager()
}
}
bool Manager::parseXmlDom(const pugi::xml_document& doc,
bool readOnly,
const std::string& libraryPath,
bool trustLibrary)
const bool readOnly,
const std::string& libraryPath)
{
pugi::xml_node libraryNode = doc.child("library");
@@ -62,10 +59,14 @@ bool Manager::parseXmlDom(const pugi::xml_document& doc,
book.setReadOnly(readOnly);
book.updateFromXml(bookNode,
removeLastPathElement(libraryPath));
removeLastPathElement(libraryPath, true, false));
if (!trustLibrary && !book.getPath().empty()) {
this->readBookFromPath(book.getPath(), &book);
/* Update the book properties with the new importer */
if (libraryVersion.empty()
|| atoi(libraryVersion.c_str()) <= atoi(KIWIX_LIBRARY_VERSION)) {
if (!book.getPath().empty()) {
this->readBookFromPath(book.getPath(), &book);
}
}
manipulator->addBookToLibrary(book);
}
@@ -74,16 +75,15 @@ bool Manager::parseXmlDom(const pugi::xml_document& doc,
}
bool Manager::readXml(const std::string& xml,
bool readOnly,
const std::string& libraryPath,
bool trustLibrary)
const bool readOnly,
const std::string& libraryPath)
{
pugi::xml_document doc;
pugi::xml_parse_result result
= doc.load_buffer_inplace((void*)xml.data(), xml.size());
if (result) {
this->parseXmlDom(doc, readOnly, libraryPath, trustLibrary);
this->parseXmlDom(doc, readOnly, libraryPath);
}
return true;
@@ -134,22 +134,21 @@ bool Manager::readOpds(const std::string& content, const std::string& urlHost)
return false;
}
bool Manager::readFile(
const std::string& path,
bool readOnly,
bool trustLibrary)
bool Manager::readFile(const std::string& path, const bool readOnly)
{
return this->readFile(path, path, readOnly);
}
bool Manager::readFile(const std::string& nativePath,
const std::string& UTF8Path,
const bool readOnly)
{
bool retVal = true;
pugi::xml_document doc;
#ifdef _WIN32
pugi::xml_parse_result result = doc.load_file(Utf8ToWide(path).c_str());
#else
pugi::xml_parse_result result = doc.load_file(path.c_str());
#endif
pugi::xml_parse_result result = doc.load_file(nativePath.c_str());
if (result) {
this->parseXmlDom(doc, readOnly, path, trustLibrary);
this->parseXmlDom(doc, readOnly, UTF8Path);
} else {
retVal = false;
}
@@ -158,7 +157,7 @@ bool Manager::readFile(
* able to know where to save the library if new content are
* available */
if (!readOnly) {
this->writableLibraryPath = path;
this->writableLibraryPath = UTF8Path;
}
return retVal;
@@ -175,10 +174,10 @@ std::string Manager::addBookFromPathAndGetId(const std::string& pathToOpen,
kiwix::Book book;
if (this->readBookFromPath(pathToOpen, &book)) {
if (!pathToSave.empty() && pathToSave != pathToOpen) {
if (pathToSave != pathToOpen) {
book.setPath(isRelativePath(pathToSave)
? computeAbsolutePath(
removeLastPathElement(writableLibraryPath),
removeLastPathElement(writableLibraryPath, true, false),
pathToSave)
: pathToSave);
}
@@ -209,15 +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;
}
@@ -225,27 +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;
}
}

View File

@@ -1,29 +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/etag.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
@@ -33,14 +26,20 @@ else
kiwix_sources += 'subprocess_unix.cpp'
endif
if 'android' in wrapper
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')
else
install_dir = get_option('libdir')
endif
if 'android' in wrapper or 'java' in wrapper
subdir('wrapper/java')
if has_ctpp2_dep
kiwix_sources += ['ctpp2/CTPP2VMStringLoader.cpp']
endif
config_h = configure_file(output : 'kiwix_config.h',
@@ -54,4 +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')

View File

@@ -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);
}
}

View File

@@ -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;
@@ -70,17 +62,11 @@ void OPDSDumper::setOpenSearchInfo(int totalResults, int startIndex, int count)
pugi::xml_node OPDSDumper::handleBook(Book book, pugi::xml_node root_node) {
auto entry_node = root_node.append_child("entry");
ADD_TEXT_ENTRY(entry_node, "id", "urn:uuid:"+book.getId());
ADD_TEXT_ENTRY(entry_node, "title", book.getTitle());
ADD_TEXT_ENTRY(entry_node, "summary", book.getDescription());
ADD_TEXT_ENTRY(entry_node, "language", book.getLanguage());
ADD_TEXT_ENTRY(entry_node, "updated", gen_date_from_yyyy_mm_dd(book.getDate()));
ADD_TEXT_ENTRY(entry_node, "name", book.getName());
ADD_TEXT_ENTRY(entry_node, "flavour", book.getFlavour());
ADD_TEXT_ENTRY(entry_node, "tags", book.getTags());
ADD_TEXT_ENTRY(entry_node, "articleCount", to_string(book.getArticleCount()));
ADD_TEXT_ENTRY(entry_node, "mediaCount", to_string(book.getMediaCount()));
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", date);
ADD_TEXT_ENTRY(entry_node, "summary", book.getDescription());
auto content_node = entry_node.append_child("link");
content_node.append_attribute("type") = "text/html";
@@ -89,9 +75,6 @@ pugi::xml_node OPDSDumper::handleBook(Book book, pugi::xml_node root_node) {
auto author_node = entry_node.append_child("author");
ADD_TEXT_ENTRY(author_node, "name", book.getCreator());
auto publisher_node = entry_node.append_child("publisher");
ADD_TEXT_ENTRY(publisher_node, "name", book.getPublisher());
if (! book.getUrl().empty()) {
auto acquisition_link = entry_node.append_child("link");
acquisition_link.append_attribute("rel") = "http://opds-spec.org/acquisition/open-access";

View File

@@ -22,8 +22,6 @@
#include <zim/search.h>
#include "tools/otherTools.h"
inline char hi(char v)
{
char hex[] = "0123456789abcdef";
@@ -243,6 +241,8 @@ Entry Reader::getMainPage() const
throw NoEntry();
}
string url = "";
zim::Article article;
if (this->zimFileHandler->getFileheader().hasMainPage())
{
@@ -260,7 +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 {
@@ -280,7 +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);
@@ -291,17 +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(), '_', ' ');
@@ -311,98 +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;
}
string Reader::getTags(bool original) const
string Reader::getCreator() 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("Creator", value);
return value;
}
string Reader::getTagStr(const std::string& tagName) const
string Reader::getPublisher() const
{
string tags_str;
getMetadata("Tags", tags_str);
return getTagValueFromTagList(convertTags(tags_str), tagName);
string value;
this->getMetatag("Publisher", value);
return value;
}
bool Reader::getTagBool(const std::string& tagName) const
{
return convertStrToBool(getTagStr(tagName));
}
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 "";
}
@@ -714,6 +674,7 @@ bool Reader::searchSuggestions(const string& prefix,
const bool reset)
{
bool retVal = false;
zim::File::const_iterator articleItr;
/* Reset the suggestions otherwise check if the suggestions number is less
* than the suggestionsCount */
@@ -731,7 +692,7 @@ bool Reader::searchSuggestions(const string& prefix,
return false;
}
for (auto articleItr = zimFileHandler->findByTitle('A', prefix);
for (articleItr = zimFileHandler->findByTitle('A', prefix);
articleItr != zimFileHandler->end()
&& articleItr->getTitle().compare(0, prefix.size(), prefix) == 0
&& this->suggestions.size() < suggestionsCount;
@@ -801,21 +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());

View File

@@ -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();
}
}

View File

@@ -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();
}
@@ -81,23 +117,18 @@ 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(const std::string& search,
void Searcher::search(std::string& search,
unsigned int resultStart,
unsigned int resultEnd,
const bool verbose)
@@ -108,27 +139,47 @@ void Searcher::search(const 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
}

View File

@@ -1,965 +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;
typedef kainjow::mustache::data MustacheData;
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,
bool blockExternalLinks);
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: // functions
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_304(const RequestContext& request, const ETag& etag) const;
Response build_redirect(const std::string& bookName, const kiwix::Entry& entry) const;
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_captured_external(const RequestContext& request);
Response handle_content(const RequestContext& request);
MustacheData get_default_data() const;
MustacheData homepage_data() const;
Response get_default_response() const;
std::shared_ptr<Reader> get_reader(const std::string& bookName) const;
bool etag_not_needed(const RequestContext& r) const;
ETag get_matching_if_none_match_etag(const RequestContext& request) const;
private: // data
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;
bool m_blockExternalLinks;
struct MHD_Daemon* mp_daemon;
Library* mp_library;
NameMapper* mp_nameMapper;
std::string m_server_id;
};
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,
m_blockExternalLinks));
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,
bool blockExternalLinks) :
m_addr(addr),
m_port(port),
m_root(root),
m_nbThreads(nbThreads),
m_verbose(verbose),
m_withTaskbar(withTaskbar),
m_withLibraryButton(withLibraryButton),
m_blockExternalLinks(blockExternalLinks),
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;
}
auto server_start_time = std::chrono::system_clock::now().time_since_epoch();
m_server_id = kiwix::to_string(server_start_time.count());
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
&& request.get_method() != RequestMethod::HEAD) {
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();
}
}
if (response.getReturnCode() == MHD_HTTP_OK && !etag_not_needed(request))
response.set_server_id(m_server_id);
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::build_304(const RequestContext& request, const ETag& etag) const
{
auto response = get_default_response();
response.set_code(MHD_HTTP_NOT_MODIFIED);
response.set_etag(etag);
response.set_content("");
return response;
}
Response InternalServer::handle_request(const RequestContext& request)
{
try {
if (! request.is_valid_url())
return build_404(request, "");
const ETag etag = get_matching_if_none_match_etag(request);
if ( etag )
return build_304(request, etag);
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);
if (request.get_url() == "/catch/external")
return handle_captured_external(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");
}
}
MustacheData InternalServer::get_default_data() const
{
MustacheData data;
data.set("root", m_root);
return data;
}
Response InternalServer::get_default_response() const
{
return Response(m_root, m_verbose.load(), m_withTaskbar, m_withLibraryButton, m_blockExternalLinks);
}
Response InternalServer::build_404(const RequestContext& request,
const std::string& bookName)
{
MustacheData 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)
{
MustacheData data;
data.set("error", msg);
Response response(m_root, true, false, 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;
}
MustacheData InternalServer::homepage_data() const
{
auto data = get_default_data();
MustacheData books{MustacheData::type::list};
for (auto& bookId: mp_library->filter(kiwix::Filter().local(true).valid(true))) {
auto& currentBook = mp_library->getBookById(bookId);
MustacheData 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);
return data;
}
bool InternalServer::etag_not_needed(const RequestContext& request) const
{
const std::string url = request.get_url();
return kiwix::startsWith(url, "/catalog")
|| url == "/search"
|| url == "/suggest"
|| url == "/random"
|| url == "/catch/external";
}
ETag
InternalServer::get_matching_if_none_match_etag(const RequestContext& r) const
{
try {
const std::string etag_list = r.get_header(MHD_HTTP_HEADER_IF_NONE_MATCH);
return ETag::match(etag_list, m_server_id);
} catch (const std::out_of_range&) {
return ETag();
}
}
Response InternalServer::build_homepage(const RequestContext& request)
{
auto response = get_default_response();
response.set_template(RESOURCE::templates::index_html, homepage_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_cacheable();
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());
}
MustacheData results{MustacheData::type::list};
bool first = true;
if (reader != nullptr) {
/* Get the suggestions */
reader->searchSuggestionsSmart(term, maxSuggestionCount);
while (reader->getNextSuggestion(suggestion)) {
MustacheData 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()) {
MustacheData 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_cacheable();
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();
return build_redirect(bookName, entry.getFinalEntry());
} catch(kiwix::NoEntry& e) {
return build_404(request, bookName);
}
}
Response InternalServer::handle_captured_external(const RequestContext& request)
{
std::string source = "";
try {
source = kiwix::urlDecode(request.get_argument("source"));
} catch (const std::out_of_range& e) {}
if (source.empty())
return build_404(request, "");
auto data = get_default_data();
data.set("source", source);
auto response = get_default_response();
response.set_template(RESOURCE::templates::captured_external_html, data);
response.set_mimeType("text/html; charset=utf-8");
response.set_compress(true);
response.set_taskbar("", "");
return response;
}
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.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") {
auto filter = kiwix::Filter().valid(true).local(true).remote(true);
string query("<Empty query>");
size_t count(10);
size_t startIndex(0);
try {
query = request.get_argument("q");
filter.query(query);
} catch (const std::out_of_range&) {}
try {
filter.maxSize(extractFromString<unsigned long>(request.get_argument("maxsize")));
} catch (...) {}
try {
filter.name(request.get_argument("name"));
} catch (const std::out_of_range&) {}
try {
filter.lang(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 {
filter.acceptTags(kiwix::split(request.get_argument("tag"), ";"));
} catch (...) {}
try {
filter.rejectTags(kiwix::split(request.get_argument("notag"), ";"));
} catch (...) {}
opdsDumper.setTitle("Search result for " + query);
uuid = zim::Uuid::generate();
bookIdsToDump = mp_library->filter(filter);
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());
}
opdsDumper.setId(kiwix::to_string(uuid));
response.set_content(opdsDumper.dumpOPDSFeed(bookIdsToDump));
return response;
}
namespace
{
std::string get_book_name(const RequestContext& request)
{
try {
return request.get_url_part(0);
} catch (const std::out_of_range& e) {
return std::string();
}
}
} // unnamed namespace
std::shared_ptr<Reader>
InternalServer::get_reader(const std::string& bookName) const
{
std::shared_ptr<Reader> reader;
try {
const std::string bookId = mp_nameMapper->getIdForName(bookName);
reader = mp_library->getReaderById(bookId);
} catch (const std::out_of_range& e) {
}
return reader;
}
Response
InternalServer::build_redirect(const std::string& bookName, const kiwix::Entry& entry) const
{
auto response = get_default_response();
response.set_redirection(m_root + "/" + bookName + "/" +
kiwix::urlEncode(entry.getPath()));
return response;
}
Response InternalServer::handle_content(const RequestContext& request)
{
if (m_verbose.load()) {
printf("** running handle_content\n");
}
const std::string bookName = get_book_name(request);
if (bookName.empty())
return build_homepage(request);
const std::shared_ptr<Reader> reader = get_reader(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);
}
kiwix::Entry entry;
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.
return build_redirect(bookName, entry.getFinalEntry());
}
} catch(kiwix::NoEntry& e) {
if (m_verbose.load())
printf("Failed to find %s\n", urlStr.c_str());
return build_404(request, bookName);
}
auto response = get_default_response();
response.set_entry(entry, request);
if (m_verbose.load()) {
printf("Found %s\n", entry.getPath().c_str());
printf("mimeType: %s\n", response.get_mimeType().c_str());
}
if (response.get_mimeType().find("text/html") != string::npos)
response.set_taskbar(bookName, reader->getTitle());
return response;
}
}

View File

@@ -1,135 +0,0 @@
/*
* Copyright 2020 Veloman Yunkan <veloman.yunkan@gmail.com>
*
* 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 "etag.h"
#include "tools/stringTools.h"
#include <algorithm>
#include <sstream>
namespace kiwix {
namespace {
// Characters in the options part of the ETag could in principle be picked up
// from the latin alphabet in natural order (the character corresponding to
// ETag::Option opt would be 'a'+opt; that would somewhat simplify the code in
// this file). However it is better to have some mnemonics in the option names,
// hence below variable: all_options[opt] corresponds to the character going
// into the ETag for ETag::Option opt.
// IMPORTANT: The characters in all_options must come in sorted order (so that
// IMPORTANT: isValidOptionsString() works correctly).
const char all_options[] = "cz";
static_assert(ETag::OPTION_COUNT == sizeof(all_options) - 1, "");
bool isValidServerId(const std::string& s)
{
return !s.empty() && s.find_first_of("\"/") == std::string::npos;
}
bool isSubsequenceOf(const std::string& s, const std::string& sortedString)
{
std::string::size_type i = 0;
for ( const char c : s )
{
const std::string::size_type j = sortedString.find(c, i);
if ( j == std::string::npos )
return false;
i = j+1;
}
return true;
}
bool isValidOptionsString(const std::string& s)
{
return isSubsequenceOf(s, all_options);
}
} // namespace
void ETag::set_option(Option opt)
{
if ( ! get_option(opt) )
{
m_options.push_back(all_options[opt]);
std::sort(m_options.begin(), m_options.end());
}
}
bool ETag::get_option(Option opt) const
{
return m_options.find(all_options[opt]) != std::string::npos;
}
std::string ETag::get_etag() const
{
if ( m_serverId.empty() )
return std::string();
return "\"" + m_serverId + "/" + m_options + "\"";
}
ETag::ETag(const std::string& serverId, const std::string& options)
{
if ( isValidServerId(serverId) && isValidOptionsString(options) )
{
m_serverId = serverId;
m_options = options;
}
}
ETag ETag::parse(std::string s)
{
if ( kiwix::startsWith("W/", s) )
s = s.substr(2);
if ( s.front() != '"' || s.back() != '"' )
return ETag();
s = s.substr(1, s.size()-2);
const std::string::size_type i = s.find('/');
if ( i == std::string::npos )
return ETag();
return ETag(s.substr(0, i), s.substr(i+1));
}
ETag ETag::match(const std::string& etags, const std::string& server_id)
{
std::istringstream ss(etags);
std::string etag_str;
while ( ss >> etag_str )
{
if ( etag_str.back() == ',' )
etag_str.pop_back();
const ETag etag = parse(etag_str);
if ( etag && etag.m_serverId == server_id )
return etag;
}
return ETag();
}
} // namespace kiwix

View File

@@ -1,85 +0,0 @@
/*
* Copyright 2020 Veloman Yunkan <veloman.yunkan@gmail.com>
*
* 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_ETAG_H
#define KIWIXLIB_SERVER_ETAG_H
#include <string>
namespace kiwix {
// The ETag string used by Kiwix server (more precisely, its value inside the
// double quotes) consists of two parts:
//
// 1. ServerId - The string obtained on server start up
//
// 2. Options - Zero or more characters encoding the values of some of the
// headers of the response
//
// The two parts are separated with a slash (/) symbol (which is always present,
// even when the the options part is empty). Neither portion of a Kiwix ETag
// may contain the slash symbol.
// Examples of valid Kiwix server ETags (including the double quotes):
//
// "abcdefghijklmn/"
// "1234567890/z"
// "1234567890/cz"
//
// The options part of the Kiwix ETag allows to correctly set the required
// headers when responding to a conditional If-None-Match request with a 304
// (Not Modified) response without following the full code path that would
// discover the necessary options.
class ETag
{
public: // types
enum Option {
CACHEABLE_ENTITY,
COMPRESSED_CONTENT,
OPTION_COUNT
};
public: // functions
ETag() {}
void set_server_id(const std::string& id) { m_serverId = id; }
void set_option(Option opt);
explicit operator bool() const { return !m_serverId.empty(); }
bool get_option(Option opt) const;
std::string get_etag() const;
static ETag match(const std::string& etags, const std::string& server_id);
private: // functions
ETag(const std::string& serverId, const std::string& options);
static ETag parse(std::string s);
private: // data
std::string m_serverId;
std::string m_options;
};
} // namespace kiwix
#endif // KIWIXLIB_SERVER_ETAG_H

View File

@@ -1,208 +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);
namespace {
RequestMethod str2RequestMethod(const std::string& method) {
if (method == "GET") return RequestMethod::GET;
else if (method == "HEAD") return RequestMethod::HEAD;
else if (method == "POST") return RequestMethod::POST;
else if (method == "PUT") return RequestMethod::PUT;
else if (method == "DELETE") return RequestMethod::DELETE_;
else if (method == "CONNECT") return RequestMethod::CONNECT;
else if (method == "OPTIONS") return RequestMethod::OPTIONS;
else if (method == "TRACE") return RequestMethod::TRACE;
else if (method == "PATCH") return RequestMethod::PATCH;
else return RequestMethod::OTHER;
}
std::string
fullURL2LocalURL(const std::string& full_url, const std::string& rootLocation)
{
if (rootLocation.empty()) {
// nothing special to handle.
return full_url;
} else if (full_url == rootLocation) {
return "/";
} else if (full_url.size() > rootLocation.size() &&
full_url.substr(0, rootLocation.size()+1) == rootLocation + "/") {
return full_url.substr(rootLocation.size());
} else {
return "";
}
}
} // unnamed namespace
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(fullURL2LocalURL(_url, rootLocation)),
method(str2RequestMethod(_method)),
version(version),
requestIndex(s_requestIndex++),
acceptEncodingDeflate(false),
accept_range(false),
range_pair(0, -1)
{
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);
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("full_url: %s\n", full_url.c_str());
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", is_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 !url.empty();
}
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);
}
}

View File

@@ -1,112 +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: // types
typedef std::pair<int, int> ByteRange;
public: // functions
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;
ByteRange get_range() const;
bool can_compress() const { return acceptEncodingDeflate; }
private: // data
std::string full_url;
std::string url;
RequestMethod method;
std::string version;
unsigned long long requestIndex;
bool acceptEncodingDeflate;
bool accept_range;
ByteRange range_pair;
std::map<std::string, std::string> headers;
std::map<std::string, std::string> arguments;
private: // functions
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

View File

@@ -1,345 +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 {
namespace
{
// some utilities
std::string get_mime_type(const kiwix::Entry& entry)
{
try {
return entry.getMimetype();
} catch (exception& e) {
return "application/octet-stream";
}
}
bool is_compressible_mime_type(const std::string& mimeType)
{
return mimeType.find("text/") != string::npos
|| mimeType.find("application/javascript") != string::npos
|| mimeType.find("application/atom") != string::npos
|| mimeType.find("application/opensearchdescription") != string::npos
|| mimeType.find("application/json") != string::npos;
}
int get_range_len(const kiwix::Entry& entry, RequestContext::ByteRange range)
{
return range.second == -1
? entry.getSize() - range.first
: range.second - range.first;
}
} // unnamed namespace
Response::Response(const std::string& root, bool verbose, bool withTaskbar, bool withLibraryButton, bool blockExternalLinks)
: m_verbose(verbose),
m_root(root),
m_content(""),
m_mimeType(""),
m_returnCode(MHD_HTTP_OK),
m_withTaskbar(withTaskbar),
m_withLibraryButton(withLibraryButton),
m_blockExternalLinks(blockExternalLinks),
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);
}
void Response::inject_externallinks_blocker()
{
kainjow::mustache::data data;
data.set("root", m_root);
auto script_tag = render_template(RESOURCE::templates::external_blocker_part_html, data);
m_content = appendToFirstOccurence(
m_content,
"<head>",
script_tag);
}
bool
Response::can_compress(const RequestContext& request) const
{
return request.can_compress()
&& is_compressible_mime_type(m_mimeType)
&& (m_content.size() > KIWIX_MIN_CONTENT_SIZE_TO_DEFLATE);
}
MHD_Response*
Response::create_raw_content_mhd_response(const RequestContext& request)
{
if (m_addTaskbar) {
introduce_taskbar();
}
if ( m_blockExternalLinks ) {
inject_externallinks_blocker();
}
bool shouldCompress = m_compress && can_compress(request);
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);
m_etag.set_option(ETag::COMPRESSED_CONTENT);
} else {
shouldCompress = false;
}
}
MHD_Response* response = MHD_create_response_from_buffer(
m_content.size(), const_cast<char*>(m_content.data()), MHD_RESPMEM_MUST_COPY);
// At shis point m_etag.get_option(ETag::COMPRESSED_CONTENT) and
// shouldCompress can have different values. This can happen for a 304 (Not
// Modified) response generated while handling a conditional If-None-Match
// request. In that case the m_etag (together with its COMPRESSED_CONTENT
// option) is obtained from the ETag list of the If-None-Match header and the
// response has no body (which shouldn't be compressed).
if ( m_etag.get_option(ETag::COMPRESSED_CONTENT) ) {
MHD_add_response_header(
response, MHD_HTTP_HEADER_VARY, "Accept-Encoding");
}
if (shouldCompress) {
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());
return response;
}
MHD_Response*
Response::create_redirection_mhd_response() const
{
MHD_Response* 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());
return response;
}
MHD_Response*
Response::create_entry_mhd_response() const
{
MHD_Response* 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());
return response;
}
MHD_Response*
Response::create_mhd_response(const RequestContext& request)
{
switch (m_mode) {
case ResponseMode::RAW_CONTENT :
return create_raw_content_mhd_response(request);
case ResponseMode::REDIRECTION :
return create_redirection_mhd_response();
case ResponseMode::ENTRY :
return create_entry_mhd_response();
}
return nullptr;
}
int Response::send(const RequestContext& request, MHD_Connection* connection)
{
MHD_Response* response = create_mhd_response(request);
MHD_add_response_header(response, "Access-Control-Allow-Origin", "*");
MHD_add_response_header(response, MHD_HTTP_HEADER_CACHE_CONTROL,
m_etag.get_option(ETag::CACHEABLE_ENTITY) ? "max-age=2723040, public" : "no-cache, no-store, must-revalidate");
const std::string etag = m_etag.get_etag();
if ( ! etag.empty() )
MHD_add_response_header(response, MHD_HTTP_HEADER_ETAG, etag.c_str());
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, const RequestContext& request) {
m_entry = entry;
m_mode = ResponseMode::ENTRY;
const std::string mimeType = get_mime_type(entry);
set_mimeType(mimeType);
set_cacheable();
if ( is_compressible_mime_type(mimeType) ) {
zim::Blob raw_content = entry.getBlob();
const std::string content = string(raw_content.data(), raw_content.size());
set_content(content);
set_compress(true);
} else {
const int range_len = get_range_len(entry, request.get_range());
set_range_first(request.get_range().first);
set_range_len(range_len);
}
}
void Response::set_taskbar(const std::string& bookName, const std::string& bookTitle)
{
m_addTaskbar = true;
m_bookName = bookName;
m_bookTitle = bookTitle;
}
}

View File

@@ -1,103 +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"
#include "etag.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, bool blockExternalLinks);
~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, const RequestContext& request);
void set_mimeType(const std::string& mimeType) { m_mimeType = mimeType; }
void set_code(int code) { m_returnCode = code; }
void set_cacheable() { m_etag.set_option(ETag::CACHEABLE_ENTITY); }
void set_server_id(const std::string& id) { m_etag.set_server_id(id); }
void set_etag(const ETag& etag) { m_etag = etag; }
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() const { return m_returnCode; }
std::string get_mimeType() const { return m_mimeType; }
void introduce_taskbar();
void inject_externallinks_blocker();
bool can_compress(const RequestContext& request) const;
private: // functions
MHD_Response* create_mhd_response(const RequestContext& request);
MHD_Response* create_raw_content_mhd_response(const RequestContext& request);
MHD_Response* create_redirection_mhd_response() const;
MHD_Response* create_entry_mhd_response() const;
private: // data
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_blockExternalLinks;
bool m_compress;
bool m_addTaskbar;
std::string m_bookName;
std::string m_bookTitle;
uint64_t m_startRange;
uint64_t m_lenRange;
ETag m_etag;
};
}
#endif //KIWIXLIB_SERVER_RESPONSE_H

View File

@@ -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;

Some files were not shown because too many files have changed in this diff Show More