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
|
import re
import ast
import os
import json
import panflute as pf
CONFIG_KEYS = {
"startLine": int,
"endLine": int,
"snippetStart": str,
"snippetEnd": str,
"xslt": str,
"includeSnippetDelimiters": bool,
"incrementSection": int,
"dedent": int,
"format": str,
"raw": str
}
# The temp filename should be fixed
# in order to be found by subprocesses
TEMP_FILE = '.temp.pandoc-include'
def parseBoolValue(val):
# use 1 or 0 (otherwise default to true if not empty)
return val and val != "0"
# Keys for env config
class Env:
# Throw error when included file not found
NotFoundError = False
# Pandoc binary for parsing included files
PandocBin = None
def parse():
Env.NotFoundError = parseBoolValue(os.environ.get("PANDOC_INCLUDE_NOT_FOUND_ERROR", "0"))
Env.PandocBin = os.environ.get("PANDOC_BIN") or None
def parseConfig(text):
regex = re.compile(
r'''
(?P<key>\w+)= # Key consists of only alphanumerics
(?P<quote>["'`]?) # Optional quote character.
(?P<value>.*?) # Value is a non greedy match
(?P=quote) # Closing quote equals the first.
($|,) # Entry ends with comma or end of string
''',
re.VERBOSE
)
config = {}
for match in regex.finditer(text):
key = match.group('key')
if key in CONFIG_KEYS:
# Include the original quotes
raw_value = f"{match.group('quote')}{match.group('value')}{match.group('quote')}"
try:
value = ast.literal_eval(raw_value)
except:
raise ValueError(f"Invalid config: {key}={raw_value}")
if not isinstance(value, CONFIG_KEYS[key]):
raise ValueError(f"Invalid value type: {key}={raw_value}")
config[key] = value
else:
pf.debug("[Warn] Invalid config key: " + key)
return config
defaultOptions = {
"include-entry": {
"path": ".",
"entered": False
},
"current-path": ".",
"include-resources": ".",
"process-path": None,
"include-order": "natural",
"rewrite-path": True,
"pandoc-options": ["--filter=pandoc-include"]
}
def parseOptions(doc):
if os.path.isfile(TEMP_FILE):
with open(TEMP_FILE, 'r') as f:
# merge with default options to prevent missing keys
options = { **defaultOptions, **json.load(f) }
else:
# entry file (default values)
options = defaultOptions.copy()
# include entry
include_entry = doc.get_metadata('include-entry')
if include_entry is not None:
if not options["include-entry"]["entered"]:
options['include-entry'] = dict(path=include_entry, entered=False)
else:
pf.debug("[WARN] include-entry specified multiple times")
# pandoc options
pandoc_options = doc.get_metadata('pandoc-options')
if pandoc_options is not None:
# Replace em-dash to double dashes in smart typography
for i in range(len(pandoc_options)):
pandoc_options[i] = pandoc_options[i].replace('\u2013', '--')
options['pandoc-options'] = pandoc_options
# order of included files (natural, alphabetical, shell_default)
include_order = doc.get_metadata("include-order")
if include_order is not None:
options["include-order"] = include_order
# rewrite path
rewrite_path = doc.get_metadata("rewrite-path")
if rewrite_path is not None:
options["rewrite-path"] = rewrite_path
# resource path
resource_path = doc.get_metadata("include-resources")
if resource_path is not None:
options["include-resources"] = resource_path
# process path
process_path = os.getcwd()
if options["process-path"] is None:
options["process-path"] = process_path
return options
|
