mirror of
https://github.com/cosinekitty/astronomy.git
synced 2025-12-30 02:58:42 -05:00
c86445ccce
The program 'realpath' does not come installed on Mac OS. This caused the bash script 'makedoc' to fail on Mac. The only place I used realpath was to convert relative paths to absolute paths for filenames passed to check_internal_links.py. It turns out Python has a standard function os.path.realpath() that does the same thing, so I moved the logic into the Python script itself. Thus makedoc no longer needs the realpath program, and the Python function will work on all platforms. There is a general lesson here: in the future I will consider moving more of my scripting logic into Python. It has proven to be more portable than a mixture of bash scripts and Windows batch files.
50 lines
1.6 KiB
Python
Executable File
50 lines
1.6 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
import sys
|
|
import re
|
|
import os
|
|
|
|
def FindBrokenLinks(text):
|
|
# Search for all link names, of the form: (#Some.Name)
|
|
linkSet = set(m.group(1) for m in re.finditer(r'\(#([A-Za-z0-9_\.]+)\)', text))
|
|
# Search for all anchor names, of the form: <a name="Some.Name">
|
|
anchorSet = set(m.group(1) for m in re.finditer(r'<\s*a\s+name\s*=\s*"([A-Za-z0-9_\.]+)"\s*>', text))
|
|
# Find all link names for which there is no matching anchor name.
|
|
return sorted(linkSet - anchorSet)
|
|
|
|
def FindBogusLinks(text):
|
|
# Search for bogus links of the form [Symbol](Symbol).
|
|
bogusSet = set()
|
|
for m in re.finditer(r'\[([A-Za-z0-9_\.]+)\]\(([A-Za-z0-9_\.]+)\)', text):
|
|
if m.group(1) == m.group(2):
|
|
bogusSet.add(m.group(1))
|
|
return bogusSet
|
|
|
|
if __name__ == '__main__':
|
|
if len(sys.argv) != 2:
|
|
print('USAGE: check_internal_links.py infile.md')
|
|
sys.exit(1)
|
|
|
|
rc = 0
|
|
filename = os.path.realpath(sys.argv[1])
|
|
with open(filename, 'rt') as infile:
|
|
text = infile.read()
|
|
|
|
badLinks = FindBrokenLinks(text)
|
|
if len(badLinks) > 0:
|
|
rc = 1
|
|
print('ERROR(check_internal_links.py): The following {} links are bad in file {}'.format(len(badLinks), filename))
|
|
for name in badLinks:
|
|
print(name)
|
|
|
|
bogusLinks = FindBogusLinks(text)
|
|
if len(bogusLinks) > 0:
|
|
rc = 1
|
|
print('ERROR(check_internal_links.py): The following {} links are of the form "(Symbol)[Symbol]" in file {}'.format(len(bogusLinks), filename))
|
|
for name in bogusLinks:
|
|
print(name)
|
|
|
|
if rc == 0:
|
|
print('Links are OK in: {}'.format(filename))
|
|
|
|
sys.exit(rc)
|