-
Notifications
You must be signed in to change notification settings - Fork 8
Expand file tree
/
Copy pathMarkdown.psm1
More file actions
273 lines (257 loc) · 11.5 KB
/
Markdown.psm1
File metadata and controls
273 lines (257 loc) · 11.5 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
# SPDX-License-Identifier: GPL-3.0
Function MarkdownPack1
{
[CmdletBinding()]
param (
# OneUp configuration object
[Parameter(Mandatory)]
[object]
$config
,
# Converted page configuration object
[Parameter(Mandatory)]
[object]
$pageCfg
)
# Markup output formatting using search and replace queries against a string containing the entire markup content.
$markupPack = @(
###############################################################
# CONTENT #
###############################################################
foreach ($attachmentCfg in $pageCfg['insertedAttachments']) {
@{
description = 'Generate attachment paths'
replacements = @(
@{
searchRegex = [regex]::Escape( $attachmentCfg['object'].preferredName )
replacement = "[$( $attachmentCfg['markdownFileName'] )]($( $pageCfg['mediaPathPandoc'] )/$( $attachmentCfg['markdownFileName'] ))"
}
)
}
}
@{
description = 'Replace media (eg: images, attachments) absolute paths with relative paths'
replacements = @(
@{
# 
# to:
# 
searchRegex = [regex]::Escape("$( $pageCfg['mediaParentPathPandoc'] )/") # Add a trailing front slash
replacement = $pageCfg['levelsPrefix']
}
)
}
@{
description = 'Add heading'
replacements = @(
@{
searchRegex = '^[^\r\n]*'
replacement = & {
$heading = "# $( $pageCfg['object'].name )"
$creationDate = $pageCfg['dateTime']
$creationDay = $creationDate.DayOfWeek.ToString()
$creationMonth = (Get-Culture).DateTimeFormat.GetMonthName([int]$pageCfg['lastModifiedTime'].ToString('MM'))
if ($config['headerTimestamp']['value'] -eq 1) {
$heading += "`n`n$( $creationDay ), $( $creationMonth ) $( $pageCfg['lastModifiedTime'].ToString('d, yyyy') ) $('`')$( $pageCfg['lastModifiedTime'].ToString('HH:mm') )$('`')"
$heading += "`n`n---"
}
$heading
}
}
)
}
@{
description = 'Refactor numbered list bullet points'
replacements = @(
@{
searchRegex = '(?<=\n\s*)([a-zA-Z0-9]{1,})(?=[.]\s*)'
replacement = '1'
}
)
}
###############################################################
# CONVERSION ARTIFACTS #
###############################################################
@{
description = 'Wrap media (eg: images, attachments) paths in <> to allow media paths with spaces. Reference: https://github.com/alopezrivera/one/issues/3'
replacements = @(
@{
# 
# to:
# 
searchRegex = '(?<=!\[\]\()(.*)(?=\))'
replacement = '<$1>'
}
)
}
@{
description = 'Remove unwated whitespace, newlines, over-indentation and more'
replacements = @(
@{
searchRegex = [regex]::Escape([char]0x00A0)
replacement = ''
}
# Remove triple spaces
@{
searchRegex = '(?<=\n)(\n)(?=\n)'
replacement = ''
}
# Replace multiple spaces after list items
@{
searchRegex = '(?<=\n\s*- )([ \s\t]{1,})(?=.*?\n)'
replacement = ''
}
@{
searchRegex = '(?<=\n\s*)([0-9]+. [ \s\t]{1,})(?=.*?\n)'
replacement = '1. ' # Take chance to replace numbered list indices for '1.'
}
# Remove extra whitespace after list item markers
@{
searchRegex = '(?<=\n\s*- )([ \s\t]{1,})(?=.*?\n)'
replacement = ''
}
@{
searchRegex = '(?<=\n\s*- )([ \s\t]{1,})(?=.*?\n)'
replacement = ''
}
# Remove double newlines after unnumbered list items
@{
searchRegex = '(?<=\n\s*- .*?)(\n)(?=\n\s*-)'
replacement = ''
}
# Remove double newlines after numbered list items
@{
searchRegex = '(?<=\n\s*[0-9]+. .*?)(\n)(?=\n\s*[0-9]+.)'
replacement = ''
}
# Remove double newlines after indented paragraphs
@{
searchRegex = '(?<=\n\s{2,}[^-0-9\.]*?)(\n)(?=\n)'
replacement = ''
}
# Remove all '>' occurrences immediately following bullet lists
@{
searchRegex = '\n>[ ]*'
replacement = "`n"
}
# Remove extra newline before inline pictures
@{
searchRegex = '\n(?=\n!\[.*?\]\(.*?\))'
replacement = ''
}
# Remove extra newline before inline tables
@{
searchRegex = '\n(?=\n\|.*?\|)'
replacement = ''
}
# Remove over-indentation of list items
@{
# When regex doesn't cut it
postprocessing = {
$content = $args[0]
$lines = $content.Split("`n")
# Create new content string
$new = $lines[0]
# For each line in the output
$prevline = $new
# For each line in the content string
foreach ($line in $lines[1..($lines.Length-1)]) {
# First, match list item indents
$m = $line -match "^\s{2,}(?=[-0-9\.]{1,})"
# If there's an indented list item in the line
if ($m) {
# Retrieve the list item indent string
$match = $Matches[0]
# Replace it with a new indent string with a base indent of 2 for unnumbered and 3 for numbered lists
$baseIndent = if ($line -match "^\s{2,}(?=[0-9\.]{1,})") {
3 # For numbered list items
}else{
2 # For unnumbered list items
}
$replacement = " " * $baseIndent * ($match.length/4)
# Replace the indent string with our new one
$line = $line -replace "\s{2,}(?=[-0-9\.]{1,})", $replacement
}else{
# Else, there may still be an indented paragraph in the line
# Match list indented paragraph indents
$pm = $line -match "^\s{2,}"
if ($pm) {
# Retrieve the indent string
$match = $Matches[0]
# Replace it with a new indent string, its base indent determined by the previous line (where we expect to find the paragraph's parent list item)
# The beginning of the string may or *may not* be indented, as the paragraph could be indented under a non-indented list item
# ^\s{2,} -> ^\s*
$baseIndent = if ($prevline -match "^\s*(?=[0-9\.]{1,})") {
3 # For numbered list items
}else{
2 # For unnumbered list items
}
$replacement = " " * $baseIndent * ($match.length/4)
# Replace the indent string with our new one
$line = $line -replace "\s{2,}", $replacement
}
}
# Append line to new content string
$new = $new + "`n" + $line
# Save previous line
$prevline = $line
}
$new
}
}
)
}
###############################################################
# OPTIONAL #
###############################################################
if ($config['keepEmptyListItems']['value'] -eq 1) {
@{
description = 'Remove empty list items'
replacements = @(
@{
searchRegex = "\n[ ]*- $([char]0x00A0)\n"
replacement = ''
}
@{
searchRegex = "\n[ ]*[0-9]+. $([char]0x00A0)\n"
replacement = ''
}
)
}
}
if ($config['newlineCharacter']['value'] -eq 1) {
@{
description = "Use LF for newlines"
replacements = @(
@{
searchRegex = '\r*\n'
replacement = "`n"
}
)
}
}
if ($config['keepEscape']['value'] -eq 1) {
@{
description = "Clear all '\' characters"
replacements = @(
@{
searchRegex = [regex]::Escape('\')
replacement = ''
}
)
}
}
elseif ($config['keepEscape']['value'] -eq 2) {
@{
description = "Clear all '\' characters except those preceding alphanumeric characters"
replacements = @(
@{
searchRegex = '\\([^A-Za-z0-9])'
replacement = '$1'
}
)
}
}
)
$markupPack
}