Skip to content

Commit cffacb6

Browse files
committed
preprocess: add workaround
1 parent 1330758 commit cffacb6

File tree

2 files changed

+38
-8
lines changed

2 files changed

+38
-8
lines changed

preprocess-zh.sh

Lines changed: 12 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ VERSION="${VERSION:-$(date +%Y%m%d)}"
4646
CPUS="$(cat /proc/cpuinfo | grep -c '^processor')"
4747

4848
# package un-processed files
49-
"${_7Z}" a -mx9 -myx9 "cppreference-unprocessed-${VERSION}.7z" ./reference
49+
"${_7Z}" a -mx9 -myx9 "../cppreference-unprocessed-${VERSION}.7z" ./reference
5050

5151
# https://gist.github.com/cdown/1163649/8a35c36fdd24b373788a7057ed483a5bcd8cd43e
5252
url_encode() {
@@ -124,10 +124,20 @@ find -iname "${startup_scripts_replace}" | xargs sed -i 's/document\.write/void
124124
find -iname "${site_scripts_replace}" | xargs sed -i '1 i if(window.mw)'
125125
find -iname "${skin_scripts_replace}" | xargs sed -i '1 i if(window.mw)'
126126
find -iname '*.css' | xargs sed -i -r 's/\.\.\/([^.]+?)\.ttf/\1.ttf/ig'
127+
128+
# workaround navbar-inv-tab.png
129+
find -iname '*.css' | xargs sed -i -r 's/https?:\/\/..\.cppreference\.com\/mwiki\/skins\/cppreference2\/images/skins\/cppreference2\/images/ig'
130+
pushd "${font_path}/skins/cppreference2/images"
131+
wget -nv 'https://en.cppreference.com/mwiki/skins/cppreference2/images/navbar-inv-tab.png'
132+
popd
133+
echo Cleaning up carbonads scripts
134+
find ./ -iname '*.html' -type f | xargs -P "${CPUS}" sed -i -r 's/<script.+?carbonads\.com\/carbon\.js.+?<\/script>//ig'
127135
echo Done.
128136

137+
rm -rf 'reference/zh.cppreference.com'
138+
129139
# package processed files
130-
"${_7Z}" a -mx9 -myx9 "html-book-${VERSION}.7z" ./reference
140+
"${_7Z}" a -mx9 -myx9 "../html-book-${VERSION}.7z" ./reference
131141

132142
# move processed files to parent folder
133143
# for make_chm.sh

zh.diff

Lines changed: 26 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
diff --git a/Makefile b/Makefile
2-
index deadfe2..46abab2 100644
2+
index deadfe2..be18286 100644
33
--- a/Makefile
44
+++ b/Makefile
55
@@ -230,7 +230,7 @@ indexes:
@@ -34,7 +34,7 @@ index deadfe2..46abab2 100644
3434
- ./export.py --url=http://en.cppreference.com/mwiki reference/cppreference-export-ns0,4,8,10.xml 0 4 8 10
3535
+ ./export.py --url=https://zh.cppreference.com/mwiki reference/cppreference-export-ns0,4,8,10.xml 0 4 8 10
3636
diff --git a/commands/preprocess.py b/commands/preprocess.py
37-
index ed67174..ada56fe 100644
37+
index ed67174..aec036c 100644
3838
--- a/commands/preprocess.py
3939
+++ b/commands/preprocess.py
4040
@@ -40,15 +40,15 @@ def rearrange_archive(root):
@@ -66,6 +66,15 @@ index ed67174..ada56fe 100644
6666
path = os.path.join(root, lang + ".cppreference.com/")
6767
src_html_path = path + "w/"
6868
src_data_path = path + "mwiki/"
69+
@@ -77,7 +77,7 @@ def rearrange_archive(root):
70+
shutil.copy(os.path.join(path, 'favicon.ico'), data_path)
71+
72+
# remove what's left
73+
- shutil.rmtree(path)
74+
+ # shutil.rmtree(path)
75+
76+
# remove the XML source file
77+
for fn in fnmatch.filter(os.listdir(root), 'cppreference-export*.xml'):
6978
@@ -214,7 +214,7 @@ def has_class(el, classes_to_check):
7079
return False
7180

@@ -75,8 +84,19 @@ index ed67174..ada56fe 100644
7584
html = etree.parse(fn, parser)
7685

7786
# remove non-printable elements
87+
@@ -236,7 +236,9 @@ def preprocess_html_file(root, fn, rename_map):
88+
for el in html.xpath('/html/body/script'):
89+
if el.get('src') is not None and 'google-analytics.com/ga.js' in el.get('src'):
90+
el.getparent().remove(el)
91+
- elif el.text is not None and ('google-analytics.com/ga.js' in el.text or 'pageTracker' in el.text):
92+
+ elif el.text is not None and ('google-analytics.com/ga.js' in el.text or 'pageTracker' in el.text or '_trackPageview' in el.text):
93+
+ el.getparent().remove(el)
94+
+ elif el.get('src') is not None and 'carbonads.com/carbon.js' in el.get('src'):
95+
el.getparent().remove(el)
96+
97+
# make custom footer
7898
diff --git a/gadgets/standard_revisions-tests/base.py b/gadgets/standard_revisions-tests/base.py
79-
index 848d431..67d00f4 100644
99+
index 848d431..91a0a99 100644
80100
--- a/gadgets/standard_revisions-tests/base.py
81101
+++ b/gadgets/standard_revisions-tests/base.py
82102
@@ -27,7 +27,7 @@ import unittest, time, re
@@ -102,7 +122,7 @@ index 9aa3fc7..13294ec 100755
102122
pywikibot.config2.step = 100
103123
pywikibot.config2.put_throttle = 0
104124
diff --git a/index2ddg.py b/index2ddg.py
105-
index 9789e56..7a3a3dc 100755
125+
index 9789e56..8962791 100755
106126
--- a/index2ddg.py
107127
+++ b/index2ddg.py
108128
@@ -447,7 +447,7 @@ def process_identifier(out, redirects, root, link, item_ident, item_type,
@@ -115,7 +135,7 @@ index 9789e56..7a3a3dc 100755
115135

116136
build_redirects(redirects, item_ident, item_type)
117137
diff --git a/index_transform/browser.py b/index_transform/browser.py
118-
index d2e625c..82cb11f 100644
138+
index d2e625c..11375f2 100644
119139
--- a/index_transform/browser.py
120140
+++ b/index_transform/browser.py
121141
@@ -42,7 +42,7 @@ class Index2Browser(IndexTransform):
@@ -149,7 +169,7 @@ index cb6e8cc..a8ac18f 100755
149169
rearrange_archive(root)
150170

151171
diff --git a/tests/test_preprocess.py b/tests/test_preprocess.py
152-
index e4aa687..d6f143f 100644
172+
index e4aa687..4856f1b 100644
153173
--- a/tests/test_preprocess.py
154174
+++ b/tests/test_preprocess.py
155175
@@ -6,23 +6,23 @@ from lxml import etree

0 commit comments

Comments
 (0)