forked from immotal/shellExercise
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathmdtoc.sh
More file actions
executable file
·351 lines (316 loc) · 10.9 KB
/
mdtoc.sh
File metadata and controls
executable file
·351 lines (316 loc) · 10.9 KB
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
#!/usr/bin/env bash
# ---------------------------from github---------------------------
# https://github.com/ekalinin/github-markdown-toc
# ---------------------------from github---------------------------
#
# Steps:
#
# 1. Download corresponding html file for some README.md:
# curl -s $1
#
# 2. Discard rows where no substring 'user-content-' (github's markup):
# awk '/user-content-/ { ...
#
# 3.1 Get last number in each row like ' ... </span></a>sitemap.js</h1'.
# It's a level of the current header:
# substr($0, length($0), 1)
#
# 3.2 Get level from 3.1 and insert corresponding number of spaces before '*':
# sprintf("%*s", substr($0, length($0), 1)*3, " ")
#
# 4. Find head's text and insert it inside "* [ ... ]":
# substr($0, match($0, /a>.*<\/h/)+2, RLENGTH-5)
#
# 5. Find anchor and insert it inside "(...)":
# substr($0, match($0, "href=\"[^\"]+?\" ")+6, RLENGTH-8)
#
gh_toc_version="0.6.2"
gh_user_agent="gh-md-toc v$gh_toc_version"
#
# Download rendered into html README.md by its url.
#
#
gh_toc_load() {
local gh_url=$1
if type curl &>/dev/null; then
curl --user-agent "$gh_user_agent" -s "$gh_url"
elif type wget &>/dev/null; then
wget --user-agent="$gh_user_agent" -qO- "$gh_url"
else
echo "Please, install 'curl' or 'wget' and try again."
exit 1
fi
}
#
# Converts local md file into html by GitHub
#
# ➥ curl -X POST --data '{"text": "Hello world github/linguist#1 **cool**, and #1!"}' https://api.github.com/markdown
# <p>Hello world github/linguist#1 <strong>cool</strong>, and #1!</p>'"
gh_toc_md2html() {
local gh_file_md=$1
URL=https://api.github.com/markdown/raw
if [ ! -z "$GH_TOC_TOKEN" ]; then
TOKEN=$GH_TOC_TOKEN
else
TOKEN_FILE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/token.txt"
if [ -f "$TOKEN_FILE" ]; then
TOKEN="$(cat $TOKEN_FILE)"
fi
fi
if [ ! -z "${TOKEN}" ]; then
AUTHORIZATION="--header \"Authorization: token ${TOKEN}\""
fi
# echo $URL 1>&2
OUTPUT="$(curl -s --user-agent "$gh_user_agent" \
--data-binary @"$gh_file_md" -H "Content-Type:text/plain" \
${AUTHORIZATION} \
$URL)"
if [ "$?" != "0" ]; then
echo "XXNetworkErrorXX"
fi
if [ "$(echo "${OUTPUT}" | awk '/API rate limit exceeded/')" != "" ]; then
echo "XXRateLimitXX"
else
echo "${OUTPUT}"
fi
}
#
# Is passed string url
#
gh_is_url() {
case $1 in
https* | http*)
echo "yes";;
*)
echo "no";;
esac
}
#
# TOC generator
#
gh_toc(){
local gh_src=$1
local gh_src_copy=$1
local gh_ttl_docs=$2
local need_replace=$3
local no_backup=$4
if [ "$gh_src" = "" ]; then
echo "Please, enter URL or local path for a README.md"
exit 1
fi
# Show "TOC" string only if working with one document
if [ "$gh_ttl_docs" = "1" ]; then
echo "Table of Contents"
echo "================="
echo ""
gh_src_copy=""
fi
if [ "$(gh_is_url "$gh_src")" == "yes" ]; then
gh_toc_load "$gh_src" | gh_toc_grab "$gh_src_copy"
if [ "${PIPESTATUS[0]}" != "0" ]; then
echo "Could not load remote document."
echo "Please check your url or network connectivity"
exit 1
fi
if [ "$need_replace" = "yes" ]; then
echo
echo "!! '$gh_src' is not a local file"
echo "!! Can't insert the TOC into it."
echo
fi
else
local rawhtml=$(gh_toc_md2html "$gh_src")
if [ "$rawhtml" == "XXNetworkErrorXX" ]; then
echo "Parsing local markdown file requires access to github API"
echo "Please make sure curl is installed and check your network connectivity"
exit 1
fi
if [ "$rawhtml" == "XXRateLimitXX" ]; then
echo "Parsing local markdown file requires access to github API"
echo "Error: You exceeded the hourly limit. See: https://developer.github.com/v3/#rate-limiting"
TOKEN_FILE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/token.txt"
echo "or place GitHub auth token here: ${TOKEN_FILE}"
exit 1
fi
local toc=`echo "$rawhtml" | gh_toc_grab "$gh_src_copy"`
echo "$toc"
if [ "$need_replace" = "yes" ]; then
if grep -Fxq "<!--ts-->" $gh_src && grep -Fxq "<!--te-->" $gh_src; then
echo "Found markers"
else
echo "You don't have <!--ts--> or <!--te--> in your file...exiting"
exit 1
fi
local ts="<\!--ts-->"
local te="<\!--te-->"
local dt=`date +'%F_%H%M%S'`
local ext=".orig.${dt}"
local toc_path="${gh_src}.toc.${dt}"
local toc_footer="<!-- Added by: `whoami`, at: `date` -->"
# http://fahdshariff.blogspot.ru/2012/12/sed-mutli-line-replacement-between-two.html
# https://opus.konghy.cn/sed-refer/ 关于 {} 的使用和分号的使用
# 或者耗子叔的 https://coolshell.cn/articles/9104.html 搜索 命令打包
# clear old TOC
sed -i${ext} "/${ts}/,/${te}/{//!d;}" "$gh_src"
# create toc file
echo "${toc}" > "${toc_path}"
echo -e "\n${toc_footer}\n" >> "$toc_path"
# insert toc file
if [[ "`uname`" == "Darwin" ]]; then
sed -i "" "/${ts}/r ${toc_path}" "$gh_src"
else
sed -i "/${ts}/r ${toc_path}" "$gh_src"
fi
echo
if [ $no_backup = "yes" ]; then
rm ${toc_path} ${gh_src}${ext}
fi
echo "!! TOC was added into: '$gh_src'"
if [ -z $no_backup ]; then
echo "!! Origin version of the file: '${gh_src}${ext}'"
echo "!! TOC added into a separate file: '${toc_path}'"
fi
echo
fi
fi
}
#
# Grabber of the TOC from rendered html
#
# $1 — a source url of document.
# It's need if TOC is generated for multiple documents.
#
gh_toc_grab() {
# if closed <h[1-6]> is on the new line, then move it on the prev line
# for example:
# was: The command <code>foo1</code>
# </h1>
# became: The command <code>foo1</code></h1>
sed -e ':a' -e 'N' -e '$!ba' -e 's/\n<\/h/<\/h/g' |
# find strings that corresponds to template
grep -E -o '<a.*id="user-content-[^"]*".*</h[1-6]' |
# remove code tags
sed 's/<code>//g' | sed 's/<\/code>//g' |
# now all rows are like:
# <a id="user-content-..." href="..."><span ...></span></a> ... </h1
# format result line
# * $0 — whole string
# * last element of each row: "</hN" where N in (1,2,3,...)
echo -e "$(awk -v "gh_url=$1" '{
level = substr($0, length($0), 1)
text = substr($0, match($0, /a>.*<\/h/)+2, RLENGTH-5)
href = substr($0, match($0, "href=\"[^\"]+?\"")+6, RLENGTH-7)
print sprintf("%*s", level*3, " ") "* [" text "](" gh_url href ")" }' |
sed 'y/+/ /; s/%/\\x/g')"
}
#
# Returns filename only from full path or url
#
gh_toc_get_filename() {
echo "${1##*/}"
}
#
# Options handlers
#
gh_toc_app() {
local need_replace="no"
if [ "$1" = '--help' ] || [ $# -eq 0 ] ; then
local app_name=$(basename "$0")
echo "GitHub TOC generator ($app_name): $gh_toc_version"
echo ""
echo "Usage:"
echo " $app_name [--insert] src [src] Create TOC for a README file (url or local path)"
echo " $app_name [--no-backup] src [src] Create TOC without backup, requires <!--ts--> / <!--te--> placeholders"
echo " $app_name - Create TOC for markdown from STDIN"
echo " $app_name --help Show help"
echo " $app_name --version Show version"
return
fi
if [ "$1" = '--version' ]; then
echo "$gh_toc_version"
echo
echo "os: `lsb_release -d | cut -f 2`"
echo "kernel: `cat /proc/version`"
echo "shell: `$SHELL --version`"
echo
for tool in curl wget grep awk sed; do
printf "%-5s: " $tool
echo `$tool --version | head -n 1`
done
return
fi
if [ "$1" = "-" ]; then
if [ -z "$TMPDIR" ]; then
TMPDIR="/tmp"
elif [ -n "$TMPDIR" -a ! -d "$TMPDIR" ]; then
mkdir -p "$TMPDIR"
fi
local gh_tmp_md
gh_tmp_md=$(mktemp $TMPDIR/tmp.XXXXXX)
while read input; do
echo "$input" >> "$gh_tmp_md"
done
gh_toc_md2html "$gh_tmp_md" | gh_toc_grab ""
return
fi
if [ "$1" = '--insert' ]; then
need_replace="yes"
shift
fi
if [ "$1" = '--no-backup' ]; then
need_replace="yes"
no_backup="yes"
shift
fi
for md in "$@"
do
echo ""
gh_toc "$md" "$#" "$need_replace" "$no_backup"
done
echo ""
echo "Created by [gh-md-toc](https://github.com/ekalinin/github-markdown-toc)"
}
#
# Entry point
#
#gh_toc_app "$@"
# deal with my particular readme file
deal_my_readme() {
local readmeFile="$(pwd)/README.md"
local readmeBak="$(pwd)/README.md.bak"
local tocFile="$(pwd)/README.md.toc"
local tmp="$(pwd)/tmp"
local begin="<!--ts-->"
local end="<!--te-->"
if [ ! -e "$tocFile" ]; then
touch "$tocFile"
else
> "$tocFile"
fi
# shellcheck disable=SC2162
while read line; do
if [ "${line:0:4}" == "### " ];then
name=$(echo "$line" | awk -F "[" '{print $2}' | awk -F "]" '{print $1}')
echo "* [$name](#$name)" >> "$tocFile"
fi
done < "$readmeFile" # 读入的是 readme 文件,写入的是 toc 文件
# write tocFile content to readmeFile between <!--ts--> and <!--te-->
# clear old toc
# 这个地方有个疑问为解决,原代码,此文件第 168 行左右删除两行之间的数据(不包括两行)没有看明白,因此
# 使用了这个拙劣的方法,用了一个中间的 tmp 文件
sed -n "1,/${begin}/p;/${end}/,$ p" "${readmeFile}" > "${tmp}"
> "${readmeFile}"
cat "${tmp}" > "${readmeFile}"
# 现在明白了具体的原因了
# 是指首先匹配 begin 和 end 对应的范围,然后这个范围内,匹配 begin,使用 n 移动到下一行,然后匹配 end 行,匹配到这一行后,把不是
# 这一行的都删掉, 下面是执行的语句
# sed -i '.tmp' "/${begin}/,/${end}/{/${begin}/n;/${end}/!d}" "${readmeFile}"
# write new toc
# 这里使用 "" 的目的是,Mac 下需要指定一个备份文件,就算为空也要指定, 这里 r 的意思是指从后面对应的文件读入数据
# 详见:http://c.biancheng.net/view/4028.html
sed -i "" "/${begin}/r ${tocFile}" "${readmeFile}"
[ -f "${tocFile}" ] && rm -rf "${tocFile}"
[ -f "${readmeBak}" ] && rm -rf "${readmeBak}"
[ -f "${tmp}" ] && rm -rf "${tmp}"
}
deal_my_readme