-
Notifications
You must be signed in to change notification settings - Fork 0
/
convert-01.sh
executable file
·192 lines (160 loc) · 5.41 KB
/
convert-01.sh
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
#!/bin/bash
set -e
set -o pipefail
trap 'echo ERROR; sleep 30' ERR
#Everything looks good from the last conversion. Set this script to be a NOOP to prevent clobbering stuff.
exit 0
cd "$(dirname "$0")"
BASE="$(pwd)"
outformat="commonmark"
mapfile="$BASE/book-number-name-map.txt"
cd "$BASE/content"
if [ ! -d Cherokee-New-Testament ]; then mkdir Cherokee-New-Testament; fi
cd Cherokee-New-Testament
for x in *; do
rm -rf "$x" || true
done
#Mapping original two digit sequences to names.
cp /dev/null "$mapfile"
bookHtml="$BASE"/original/index.html
cp "$bookHtml" index.html
chmod 0644 index.html
pandoc --eol=lf --wrap=preserve -o index.md.tmp --to=$outformat --from=html "index.html"
perl -p -i -e 's|\[(.*?)\]\((.*?)\.html\)|\[$1\]\(@/Cherokee-New-Testament/$1/index.md\)|g' index.md.tmp
date="$(ls -l --time-style='+%Y-%m-%dT%H:%M:%SZ' "$bookHtml"|cut -f 6 -d ' ')"
weight="$(ls -l --time-style='+%s' "$bookHtml"|cut -f 6 -d ' ')"
bookName="About"
(
cat << EOH
+++
draft=false
date = $date
title = "$bookName - Cherokee New Testament"
weight = $weight
[taxonomies]
authors = ["Timothy Legg"]
categories = []
tags = []
[extra]
+++
EOH
) > index.md
cat index.md.tmp >> index.md
rm index.md.tmp
rm index.html
#Books are two digit sequences
for bookHtml in "$BASE"/original/[0-2][0-9].html; do
cd "$BASE/content/Cherokee-New-Testament"
date="$(ls -l --time-style='+%Y-%m-%dT%H:%M:%SZ' "$bookHtml"|cut -f 6 -d ' ')"
weight="$(ls -l --time-style='+%s' "$bookHtml"|cut -f 6 -d ' ')"
prefix="$(basename -s .html "$bookHtml")"
bookName="$(grep '<h1>' "$bookHtml" | perl -p -e 's|<h1>(.*?)</h1>|$1|g')"
echo "=== BOOK: $bookName"
printf "$prefix\t$bookName\n" >> "$mapfile"
if [ -d "$bookName" ]; then rm -r "$bookName"; fi
mkdir "$bookName"
cd "$bookName"
if [ -f "$BASE/original/$prefix"_.png ]; then
cp -p "$BASE/original/$prefix"_.png .
else
cp -v -p "$BASE/original/$prefix"0000.png "$prefix"_.png
fi
chmod 0644 *.png
cp -f "$bookHtml" index.html
chmod 0644 index.html
perl -p -i -e 's|<head>|<head><meta charset="UTF-8"/>|g' index.html
perl -p -i -e 's|(<tr><th>.*)$|\1</th></tr>|g' index.html
perl -p -i -e 's|^<br>$||g' index.html
perl -p -i -e 's|<th>|<td>|g' index.html
perl -p -i -e 's|</th>|</td>|g' index.html
#perl -p -i -e 's| width=\d+||g' index.html
perl -p -i -e 's| border=\d+||g' index.html
perl -p -i -e 's|<br>| |g' index.html
pandoc --eol=lf --wrap=preserve -o index.md.tmp --to=$outformat --from=html "index.html"
perl -p -i -e 's|\[(.*?)\]\((.*?)\.html\)|\[$1\]\(@/Cherokee-New-Testament/'"$bookName"'/$2/index.md\)|g' index.md.tmp
(
cat << EOH
+++
draft=false
date = $date
title = "$bookName - Cherokee New Testament"
weight = $weight
[taxonomies]
authors = ["Timothy Legg"]
categories = []
tags = []
[extra]
+++
EOH
) > index.md
cat index.md.tmp >> index.md
rm index.md.tmp
rm index.html
cwd="$(pwd)"
#Chapters are four digit sequences.
for chapter in "$BASE/original/$prefix"[0-9][0-9].html; do
cd "$cwd"
folder="$(basename -s .html "$chapter")"
if [ -d "$folder" ]; then rm -rf "$folder"; fi
mkdir "$folder"
cd "$folder"
date="$(ls -l --time-style='+%Y-%m-%dT%H:%M:%SZ' "$chapter"|cut -f 6 -d ' ')"
weight="$(ls -l --time-style='+%s' "$chapter"|cut -f 6 -d ' ')"
chapterPrefix="$(basename -s .html "$chapter")"
chapterNo="$(echo "$chapterPrefix"|sed "s/^${prefix}0*//")"
if [ -f "$BASE/original/$prefix"_.png ]; then
cp -p "$BASE/original/$prefix"_.png .
else
cp -v -p "$BASE/original/$prefix"0000.png "$prefix"_.png
fi
cp -p "$BASE/original/$prefix"0000.png "$prefix"0000.png
cp -p "$BASE/original/$chapterPrefix"[0-9][0-9].png .
chmod 0644 *.png
cp -p -f "$chapter" index.html
chmod 0644 index.html
perl -p -i -e 's|<head>|<head><meta charset="UTF-8"/>|g' index.html
perl -p -i -e 's|(<tr><th>.*)$|\1</th></tr>|g' index.html
perl -p -i -e 's|^<br>$||g' index.html
perl -p -i -e 's|<th>|<td>|g' index.html
perl -p -i -e 's|</th>|</td>|g' index.html
#perl -p -i -e 's| width=\d+||g' index.html
perl -p -i -e 's| border=\d+||g' index.html
perl -p -i -e 's|<br>| |g' index.html
pandoc --eol=lf --wrap=preserve -o index.md.tmp --to=$outformat --from=html "index.html"
(
cat << EOH
+++
draft=false
date = $date
title = "$bookName - Chapter $chapterNo - Cherokee New Testament"
weight = $weight
[taxonomies]
authors = ["Timothy Legg"]
categories = []
tags = []
[extra]
+++
EOH
) > index.md
cat index.md.tmp >> index.md
rm index.md.tmp
rm index.html
done
done
#Post processing fixups
cd "$BASE/content/Cherokee-New-Testament"
perl -p -i -e 's|^(.*\)) +$|* $1\n|' index.md
perl -p -i -e 's|(@/Cherokee-New-Testament/[^\)]*?) ([^\)]*)|$1-$2|' index.md
for book in *; do
cd "$BASE/content/Cherokee-New-Testament"
if [ ! -d "$book" ]; then continue; fi
xbook="$book"
if [[ "$book" == *" "* ]]; then
xbook="$(echo "$book"|sed 's| |-|g')"
mv -v "$book" "$xbook"
fi
cd "$xbook"
perl -p -i -e 's|^(.*\))$|* $1\n|' index.md
perl -p -i -e 's|(@/Cherokee-New-Testament/[^\)]*?) ([^\)]*)|$1-$2|' index.md
done
# TODO: Fix up image scaling via img tags to be relative to the original size and viewport width.