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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
|
diff --git a/.gitignore b/.gitignore
index 3768c97..d88251b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,3 +2,4 @@
build/
dist/
*.pyc
+.eggs
diff --git a/.travis.yml b/.travis.yml
index b94c4dc..8770821 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,4 +1,7 @@
os: linux
+arch:
+ - amd64
+ - ppc64le
addons:
apt:
update: true
@@ -6,8 +9,8 @@ addons:
- libchm-dev
language: python
python:
- - "3.5"
- "3.6"
- "3.7"
- "3.8"
+ - "3.9"
script: scripts/travis-run.sh
diff --git a/AUTHORS b/AUTHORS
index 23e621b..d36c3ec 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -1,3 +1,3 @@
Copyright (c) 2003 Eugeny Korekin <az@ftc.ru>
Copyright (c) 2005-2009 Basil Shubin <basil.shubin@gmail.com>
-Copyright (c) 2015,2019 Mikhail Gusarov <dottedmag@dottedmag.net>
+Copyright (c) 2015-2020 Misha Gusarov <dottedmag@dottedmag.net>
diff --git a/README.md b/README.md
index ec2b4e1..b14cec2 100644
--- a/README.md
+++ b/README.md
@@ -33,6 +33,8 @@ This feature requires `htmldoc(1)`, and `lynx(1)` or `elinks(1)` installed.
Installation
============
+Archmage uses PyCHM that depends on (C library) CHMlib. After CHMlib is installed, do
+
pip install archmage
Requirements
@@ -40,7 +42,7 @@ Requirements
arCHMage has the following dependencies:
- * Python 3.5+
+ * Python 3.6+
* PyCHM
* BeautifulSoup4
diff --git a/archmage/CHM.py b/archmage/CHM.py
index ce85446..44bbd98 100644
--- a/archmage/CHM.py
+++ b/archmage/CHM.py
@@ -3,7 +3,7 @@
# archmage -- CHM decompressor
# Copyright (c) 2003 Eugeny Korekin <aaaz@users.sourceforge.net>
# Copyright (c) 2005-2009 Basil Shubin <bashu@users.sourceforge.net>
-# Copyright (c) 2015,2019 Mikhail Gusarov <dottedmag@dottedmag.net>
+# Copyright (c) 2015-2020 Misha Gusarov <dottedmag@dottedmag.net>
#
# 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
@@ -29,6 +29,7 @@ import string
import tempfile
import os.path
from enum import Enum
+from typing import List, Union
import archmage
@@ -36,7 +37,7 @@ from archmage.CHMParser import SitemapFile, PageLister, ImageCatcher, TOCCounter
# import PyCHM bindings
try:
- from chm import chmlib
+ from chm import chmlib # type: ignore
except ImportError as msg:
sys.exit(
"ImportError: %s\nPlease check README file for system requirements."
@@ -70,7 +71,7 @@ class FileSource:
out.append(path)
return chmlib.CHM_ENUMERATOR_CONTINUE
- out = []
+ out: List[str] = []
if (
chmlib.chm_enumerate(
self._chm, chmlib.CHM_ENUMERATE_ALL, get_name, out
@@ -123,7 +124,7 @@ class CHM:
self.cache = {}
# Name of source directory with CHM content
if os.path.isdir(name):
- self.source = DirSource(name)
+ self.source: Union[DirSource, FileSource] = DirSource(name)
else:
self.source = FileSource(name)
self.sourcename = name
@@ -177,13 +178,14 @@ class CHM:
return self.cache["image_urls"]
def _image_urls(self):
- out = []
+ out: List[str] = []
image_catcher = ImageCatcher()
for file in self.html_files():
+ # Use latin-1, as it will accept any byte sequences
image_catcher.feed(
Entry(
self.source, file, self.filename_case, self.restore_framing
- ).correct()
+ ).correct().decode("latin-1")
)
for image_url in image_catcher.imgurls:
if not out.count(image_url):
@@ -273,7 +275,8 @@ class CHM:
def _toclevels(self):
counter = TOCCounter()
- counter.feed(self.topicstree)
+ # Use latin-1, as it will accept any byte sequences
+ counter.feed(self.topicstree.decode("latin-1"))
if counter.count > self.maxtoclvl:
return self.maxtoclvl
else:
@@ -432,7 +435,7 @@ class CHM:
self.extract_entry(
entry=key, output_file=key.lower(), destdir=tempdir
)
- htmldoc(files, self.htmldoc_exec, options, self.toclevels, output)
+ htmldoc(files, self.htmldoc_exec, options, self.toclevels(), output)
# Remove temporary files
shutil.rmtree(path=tempdir)
@@ -493,21 +496,21 @@ if (window.name != "content")
data = self.lower_links(data)
# Delete unwanted HTML elements.
- data = re.sub("<div .*teamlib\\.gif.*\\/div>", "", data)
- data = re.sub("<a href.*>\\[ Team LiB \\]<\\/a>", "", data)
+ data = re.sub(b"<div .*teamlib\\.gif.*\\/div>", b"", data)
+ data = re.sub(b"<a href.*>\\[ Team LiB \\]<\\/a>", b"", data)
data = re.sub(
- "<table.*larrow\\.gif.*rarrow\\.gif.*<\\/table>", "", data
+ b"<table.*larrow\\.gif.*rarrow\\.gif.*<\\/table>", b"", data
)
- data = re.sub("<a href.*next\\.gif[^>]*><\\/a>", "", data)
- data = re.sub("<a href.*previous\\.gif[^>]*><\\/a>", "", data)
- data = re.sub("<a href.*prev\\.gif[^>]*><\\/a>", "", data)
- data = re.sub('"[^"]*previous\\.gif"', '""', data)
- data = re.sub('"[^"]*prev\\.gif"', '""', data)
- data = re.sub('"[^"]*next\\.gif"', '""', data)
+ data = re.sub(b"<a href.*next\\.gif[^>]*><\\/a>", b"", data)
+ data = re.sub(b"<a href.*previous\\.gif[^>]*><\\/a>", b"", data)
+ data = re.sub(b"<a href.*prev\\.gif[^>]*><\\/a>", b"", data)
+ data = re.sub(b'"[^"]*previous\\.gif"', b'""', data)
+ data = re.sub(b'"[^"]*prev\\.gif"', b'""', data)
+ data = re.sub(b'"[^"]*next\\.gif"', b'""', data)
if data is not None:
return data
else:
- return ""
+ return b""
def get(self):
"""Get CHM entry content"""
@@ -524,4 +527,4 @@ if (window.name != "content")
if data is not None:
return data
else:
- return ""
+ return b""
diff --git a/archmage/CHMParser.py b/archmage/CHMParser.py
index 1ac1e2b..02c8c37 100644
--- a/archmage/CHMParser.py
+++ b/archmage/CHMParser.py
@@ -2,7 +2,7 @@
#
# archmage -- CHM decompressor
# Copyright (c) 2009 Basil Shubin <bashu@users.sourceforge.net>
-# Copyright (c) 2015,2019 Mikhail Gusarov <dottedmag@dottedmag.net>
+# Copyright (c) 2015-2020 Misha Gusarov <dottedmag@dottedmag.net>
#
# 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
@@ -21,9 +21,10 @@
import re
import mimetypes
-import sgmllib, urllib.request, urllib.error, urllib.parse
+import sgmllib # type: ignore
+import urllib.request, urllib.error, urllib.parse
-from bs4 import BeautifulSoup, UnicodeDammit
+from bs4 import BeautifulSoup, UnicodeDammit # type: ignore
from html.parser import HTMLParser
from urllib.parse import urlparse
diff --git a/archmage/__init__.py b/archmage/__init__.py
index 8f1d5c5..804becf 100644
--- a/archmage/__init__.py
+++ b/archmage/__init__.py
@@ -3,7 +3,7 @@
# archmage -- CHM decompressor
# Copyright (c) 2003 Eugeny Korekin <aaaz@users.sourceforge.net>
# Copyright (c) 2005-2009 Basil Shubin <bashu@users.sourceforge.net>
-# Copyright (c) 2015,2019 Mikhail Gusarov <dottedmag@dottedmag.net>
+# Copyright (c) 2015-2020 Misha Gusarov <dottedmag@dottedmag.net>
#
# 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
diff --git a/archmage/arch.conf b/archmage/arch.conf
index bb5432a..c9208a4 100644
--- a/archmage/arch.conf
+++ b/archmage/arch.conf
@@ -56,7 +56,7 @@ chmtohtml = '-t html -f "%(output)s" --book %(toc)s --no-numbered --toctitle "Ta
# CHM2PDF converting. Use following command to convert CHM content to a single
# PDF file. Make sure that htmldoc is available on your system.
-chmtopdf = '-t pdf14 -f "%(output)s" --book %(toc)s --no-numbered --toctitle "Table of Contents" --title --textcolor "#000000" --linkcolor "#0000ff" --linkstyle plain --size Universal --left 1.00in --right 0.50in --top 0.50in --bottom 0.50in --header .t. --header1 ... --footer h.1 --nup 1 --tocheader .t. --tocfooter ..i --portrait --color --no-pscommands --no-xrxcomments --compression=1 --jpeg=0 --fontsize 11.0 --fontspacing 1.2 --headingfont Helvetica --bodyfont Times --headfootsize 11.0 --headfootfont Helvetica --charset iso-8859-1 --links --embedfonts --pagemode outline --pagelayout single --firstpage c1 --pageeffect none --pageduration 10 --effectduration 1.0 --no-encryption --permissions all --owner-password "" --user-password "" --browserwidth 680 --no-strict --no-overflow --quiet'
+chmtopdf = '-t pdf14 -f "%(output)s" --webpage %(toc)s --no-title --no-numbered --toctitle "Table of Contents" --textcolor "#000000" --linkcolor "#0000ff" --linkstyle plain --size Universal --left 1.00in --right 0.50in --top 0.50in --bottom 0.50in --header .t. --header1 ... --footer h.1 --nup 1 --tocheader .t. --tocfooter ..i --portrait --color --no-pscommands --no-xrxcomments --compression=1 --jpeg=0 --fontsize 11.0 --fontspacing 1.2 --headingfont Helvetica --bodyfont Times --headfootsize 11.0 --headfootfont Helvetica --charset iso-8859-1 --links --embedfonts --pagemode outline --pagelayout single --firstpage c1 --pageeffect none --pageduration 10 --effectduration 1.0 --no-encryption --permissions all --owner-password "" --user-password "" --browserwidth 680 --no-strict --no-overflow --quiet'
# Maximum Table of Content levels for htmldoc utility.
#
diff --git a/archmage/cli.py b/archmage/cli.py
index a7fd54a..8a573f7 100755
--- a/archmage/cli.py
+++ b/archmage/cli.py
@@ -3,7 +3,7 @@
# archmage -- CHM decompressor
# Copyright (c) 2003 Eugeny Korekin <aaaz@users.sourceforge.net>
# Copyright (c) 2005-2009 Basil Shubin <bashu@users.sourceforge.net>
-# Copyright (c) 2015,2019 Mikhail Gusarov <dottedmag@dottedmag.net>
+# Copyright (c) 2015-2020 Misha Gusarov <dottedmag@dottedmag.net>
#
# 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
diff --git a/archmage/htmldoc.py b/archmage/htmldoc.py
index 606fea1..b223dfd 100644
--- a/archmage/htmldoc.py
+++ b/archmage/htmldoc.py
@@ -21,7 +21,6 @@
"""Generic converter function"""
import os
-import string
import tempfile
import subprocess
@@ -42,10 +41,10 @@ def htmldoc(input, cmd, options, toclevels, output):
options = options % {"output": output, "toc": toc}
if input:
# Create a htmldoc file for batch processing
- f = tempfile.NamedTemporaryFile(delete=False)
- f.write("#HTMLDOC 1.8.27\n")
- f.write(options + "\n")
- f.write(string.join(input, "\n"))
+ f = tempfile.NamedTemporaryFile(mode="wb", delete=False)
+ f.write(b"#HTMLDOC 1.8.27\n")
+ f.write(options.encode("utf-8") + b"\n")
+ f.write(b'\n'.join(f.encode('utf-8') for f in input))
f.close()
# Prepare command line to execute
command = "%s --batch %s" % (cmd, f.name)
diff --git a/setup.py b/setup.py
index 630a675..092372d 100644
--- a/setup.py
+++ b/setup.py
@@ -18,7 +18,7 @@ setup(
name="archmage",
version="0.4.2.1",
description="CHM decompressor",
- maintainer="Mikhail Gusarov",
+ maintainer="Misha Gusarov",
maintainer_email="dottedmag@dottedmag.net",
url="https://github.com/dottedmag/archmage",
license="GPLv2+",
|
