1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
#!/usr/bin/python3
# vim: set fileencoding=utf-8 ts=4 sts=4 sw=4 tw=80 expandtab :
# Copyright (C) 2012 Florian Bruhin <xojgrep@the-compiler.org>
# xojgrep 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
# (at your option) any later version.
#
# xojgrep 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 xojgrep. If not, see <http://www.gnu.org/licenses/>.
import sys
import os
import argparse
import gzip
import lxml.etree
import pyPdf
def main():
options = parseargs()
def istextfile(filename, blocksize=512):
""" Uses heuristics to guess whether the given file is text or binary,
by reading a single block of bytes from the file.
If more than 30% of the chars in the block are non-text, or there are NUL
('\x00') bytes in the block, assume this is a binary file.
Based on http://s.cmpl.cc/n
"""
_text_characters = (
b''.join(bytes((i,)) for i in range(32, 127)) + # Printable ASCII chars
b'\n\r\t\f\b' # Control chars commonly used in text
)
with open(filename, 'rb') as f:
block = f.read(blocksize)
if b'\x00' in block:
# Files with null bytes are binary
return False
elif not block:
# An empty file is considered a valid text file
return True
# Use translate's 'deletechars' argument to efficiently remove all
# occurrences of _text_characters from the block
nontext = block.translate(None, _text_characters)
return float(len(nontext)) / len(block) <= 0.30
def getfilelist(path):
filelist = []
for root, dirnames, filenames in os.walk(path):
filelist.append(os.path.join(root, filename))
return filelist
def parseargs():
""" Parses the command-line arguments """
parser = argparse.ArgumentParser(
description='Grep xoj, text and pdf files from one tool.',
epilog='FIXME',
)
parser.add_argument('file', nargs='+', default=None, help='File name')
options = parser.parse_args()
return options
class XOJFile:
def __init__(self, filename):
with gzip.open(filename) as f:
# FIXME check for invalid files
try:
self.tree = lxml.etree.parse(f)
except lxml.etree.XMLSyntaxError:
self.tree = None
raise # FIXME output error
def getcontent(self):
content = []
# TODO check if that works with a xournal file without texts
pagecount = len(self.tree.xpath('/xournal/page'))
for pn in range(1, pagecount + 1):
pagecontent = []
texts = self.tree.xpath('/xournal/page[{}]//text'.format(pn))
for text in texts:
pagecontent.append(text.text)
if pagecontent:
content.append((pn, pagecontent))
return content
class PDFFile:
def __init__(self, filename):
self.pdffile = open(filename, 'rb')
self.doc = pyPdf.PdfFileReader(self.pdffile)
def __del__(self):
self.pdffile.close()
def getcontent(self):
pagecount = self.doc.numPages
content = []
for pn in range(1, pagecount + 1):
page = self.doc.getPage(pn)
text = page.extractText()
if text:
content.append((pn, [text]))
return content
class TXTFile:
def __init__(self, filename):
self.txtfile = open(filename, 'r')
def __del__(self):
self.txtfile.close()
def getcontent(self):
content = []
for (ln, line) in enumerate(self.txtfile, 1):
content.append((ln, [line.rstrip('\n')]))
return content
if __name__ == '__main__':
sys.exit(main())
|
