WizardKit/scripts/msword-search

79 lines
2.1 KiB
Python
Executable file

#!/bin/python3
#
## WizardKit: MS Word content search tool
import os
import re
import sys
import wk
# STATIC VARIABLES
SCANDIR = os.getcwd()
USAGE = '''Usage: {script} <search-terms>...
e.g. {script} "Book Title" "Keyword" "etc"
This script will search all doc/docx files below the current directory for
the search-terms provided (case-insensitive).'''.format(script=__file__)
REGEX_DOC_FILES = re.compile(r'\.docx?$', re.IGNORECASE)
def scan_for_docs(path):
for entry in os.scandir(path):
if entry.is_dir(follow_symlinks=False):
yield from scan_for_docs(entry.path)
elif entry.is_file and REGEX_DOC_FILES.search(entry.name):
yield entry
def scan_file(file_path, search):
match = False
try:
if entry.name.lower().endswith('.docx'):
result = wk.exe.run_program(['unzip', '-p', entry.path])
else:
# Assuming .doc
result = wk.exe.run_program(['antiword', entry.path])
out = result.stdout.decode()
match = re.search(search, out, re.IGNORECASE)
except Exception:
# Ignore errors since files may be corrupted
pass
return entry.path if match else None
if __name__ == '__main__':
try:
# Prep
wk.ui.cli.clear_screen()
terms = [re.sub(r'\s+', r'\s*', t) for t in sys.argv[1:]]
search = '({})'.format('|'.join(terms))
if len(sys.argv) == 1:
# Print usage
wk.ui.cli.print_standard(USAGE)
else:
matches = []
for entry in scan_for_docs(SCANDIR):
matches.append(scan_file(entry.path, search))
# Strip None values (i.e. non-matching entries)
matches = [m for m in matches if m]
if matches:
wk.ui.cli.print_success('Found {} {}:'.format(
len(matches),
'Matches' if len(matches) > 1 else 'Match'))
for match in matches:
wk.ui.cli.print_standard(match)
else:
wk.ui.cli.print_error('No matches found.')
# Done
wk.ui.cli.print_standard('\nDone.')
#pause("Press Enter to exit...")
except SystemExit:
raise
except: # noqa: E722
wk.ui.cli.major_exception()
# vim: sts=2 sw=2 ts=2