/usr/share/pyshared/doconce/pandoc.py is in doconce 0.7.3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | """
Warning: This translater should be complete
(no "reference links", though), but it is
not tested.
See http://johnmacfarlane.net/pandoc/README.html
for syntax.
"""
import re, sys
from common import default_movie, plain_exercise, table_analysis
from html import html_movie
def pandoc_author(authors_and_institutions, auth2index,
inst2index, index2inst, auth2email):
# List authors on multiple lines
authors = []
for author, i, e in authors_and_institutions:
if i is None:
authors.append(author)
else:
authors.append(author + ' at ' + ' and '.join(i))
authors = '% ' + '; '.join(authors) + '\n'
return authors
def pandoc_code(filestr, format):
defs = dict(cod='Python', pycod='Python', cppcod='Cpp',
fcod='Fortran', ccod='C',
pro='Python', pypro='Python', cpppro='Cpp',
fpro='Fortran', cpro='C',
sys='Bash', dat='Python')
# (the "python" typesetting is neutral if the text
# does not parse as python)
# Code blocks apply the ~~~~~ delimiter, with blank lines before
# and after (alternative: indent code 4 spaces - not preferred)
for key in defs:
language = defs[key]
replacement = '\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~{.%s}\n' % defs[key]
#replacement = '\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~{.%s ,numberLines}\n' % defs[key] # enable line numbering
#filestr = re.sub(r'^!bc\s+%s\s*\n' % key,
# replacement, filestr, flags=re.MULTILINE)
cpattern = re.compile(r'^!bc\s+%s\s*\n' % key, flags=re.MULTILINE)
filestr = cpattern.sub(replacement, filestr)
# any !bc with/without argument becomes a cod (python) block:
#replacement = '\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~{.%s}' % defs['cod']
# or no, we then just skip any specification
replacement = '\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
#filestr = re.sub(r'^!bc.+\n', replacement, filestr, flags=re.MULTILINE)
cpattern = re.compile(r'^!bc.+$', flags=re.MULTILINE)
filestr = cpattern.sub(replacement, filestr)
filestr = re.sub(r'!ec *\n', '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n', filestr)
# Math: give warning if not only single equations
pattern = r'!bt.+?\\begin\{(.+?)\}'
cpattern = re.compile(pattern, re.DOTALL)
math_envirs = cpattern.findall(filestr)
for envir in math_envirs:
if envir not in ('equation', 'align*'):
print 'Warning: latex envir \\begin{%s} does not work well' % envir
print ' pandoc extended markdown syntax handles only single equations'
# pandoc/markdown supports LaTeX if embedded in $$
filestr = re.sub(r'!bt *\n', '$$\n', filestr)
filestr = re.sub(r'!et *\n', '$$\n', filestr)
filestr = re.sub(r'\$\$\s*\\\[', '$$', filestr)
filestr = re.sub(r'\\\]\s*\$\$', '$$', filestr)
filestr = filestr.replace(' label{', ' \\label{')
pattern = r'^label\{'
cpattern = re.compile(pattern, re.MULTILINE)
filestr = cpattern.sub('\\label{', filestr)
filestr = re.sub(r'\(ref\{(.+?)\}\)', r'\eqref{\g<1>}', filestr)
return filestr
def pandoc_table(table):
"""
Simple markdown tables look like this::
Left Right Center Default
------- ------ ---------- -------
12 12 12 12
123 123 123 123
1 1 1 1
"""
# Slight modification of rst_table
# Here is the pandoc table format
column_width = table_analysis(table['rows'])
ncolumns = len(column_width)
column_spec = table.get('columns_align', 'c'*ncolumns).replace('|', '')
heading_spec = table.get('headings_align', 'c'*ncolumns).replace('|', '')
a2py = {'r': 'rjust', 'l': 'ljust', 'c': 'center'}
s = '' # '\n'
for i, row in enumerate(table['rows']):
#s += ' ' # indentation of tables
if row == ['horizontal rule'] and i > 0 and i < len(table['rows'])-1:
# No horizontal rule at the top and bottom, just after heading
for w in column_width:
s += '-'*w + ' '
else:
# check if this is a headline between two horizontal rules:
if i == 1 and \
table['rows'][i-1] == ['horizontal rule'] and \
table['rows'][i+1] == ['horizontal rule']:
headline = True
else:
headline = False
for w, c, ha, ca in \
zip(column_width, row, heading_spec, column_spec):
if headline:
s += getattr(c, a2py[ha])(w) + ' '
elif row != ['horizontal rule']:
s += getattr(c, a2py[ca])(w) + ' '
s += '\n'
s += '\n'
return s
def pandoc_ref_and_label(section_label2title, format, filestr):
# .... see section ref{my:sec} is replaced by
# see the section "...section heading..."
pattern = r'[Ss]ection(s?)\s+ref\{'
replacement = r'the section\g<1> ref{'
filestr = re.sub(pattern, replacement, filestr)
pattern = r'[Cc]hapter(s?)\s+ref\{'
replacement = r'the chapter\g<1> ref{'
filestr = re.sub(pattern, replacement, filestr)
# Remove label{...} from output (when only label{} on a line, remove
# the newline too, leave label in figure captions, and remove all the rest)
#filestr = re.sub(r'^label\{.+?\}\s*$', '', filestr, flags=re.MULTILINE)
cpattern = re.compile(r'^label\{.+?\}\s*$', flags=re.MULTILINE)
filestr = cpattern.sub('', filestr)
#filestr = re.sub(r'^(FIGURE:.+)label\{(.+?)\}', '\g<1>{\g<2>}', filestr, flags=re.MULTILINE)
cpattern = re.compile(r'^(FIGURE:.+)label\{(.+?)\}', flags=re.MULTILINE)
filestr = cpattern.sub('\g<1>{\g<2>}', filestr)
filestr = re.sub(r'label\{.+?\}', '', filestr) # all the remaining
# Replace all references to sections. Pandoc needs a coding of
# the section header as link.
def title2pandoc(title):
# http://johnmacfarlane.net/pandoc/README.html
for c in ('?', ';', ':'):
title = title.replace(c, '')
title = title.replace(' ', '-').strip()
start = 0
for i in range(len(title)):
if title[i].isalpha():
start = i
title = title[start:]
title = title.lower()
if not title:
title = 'section'
return title
for label in section_label2title:
filestr = filestr.replace('ref{%s}' % label,
'[%s](#%s)' % (section_label2title[label],
title2pandoc(section_label2title[label])))
from common import ref2equations
filestr = ref2equations(filestr)
return filestr
def pandoc_index_bib(filestr, index, citations, bibfile):
# pandoc citations are of the form
# bla-bla, see [@Smith04, ch. 1; @Langtangen_2008]
# Method: cite{..} -> [...], doconce.py has already fixed @ and ;
filestr = re.sub(r'cite\{(.+?)\}', r'[\g<1>]', filestr)
#filestr = re.sub(r'^BIBFILE:.+$', bibtext, filestr, flags=re.MULTILINE)
cpattern = re.compile(r'^BIBFILE:.+$', flags=re.MULTILINE)
filestr = cpattern.sub('# References', filestr)
# pandoc does not support index entries,
# remove all index entries
filestr = re.sub(r'idx\{.+?\}' + '\n?', '', filestr)
return filestr
def define(FILENAME_EXTENSION,
BLANKLINE,
INLINE_TAGS_SUBST,
CODE,
LIST,
ARGLIST,
TABLE,
EXERCISE,
FIGURE_EXT,
CROSS_REFS,
INDEX_BIB,
INTRO,
OUTRO):
# all arguments are dicts and accept in-place modifications (extensions)
FILENAME_EXTENSION['pandoc'] = '.mkd'
BLANKLINE['pandoc'] = '\n'
# replacement patterns for substitutions of inline tags
INLINE_TAGS_SUBST['pandoc'] = {
'math': None, # indicates no substitution, leave as is
'math2': r'\g<begin>$\g<latexmath>$\g<end>',
'emphasize': None,
'bold': None,
'figure': r'',
#'movie': default_movie,
'movie': html_movie,
'verbatim': None,
'linkURL': r'\g<begin>\g<link> (\g<url>)\g<end>',
'linkURL2': r'[\g<link>](\g<url>)',
'linkURL3': r'[\g<link>](\g<url>)',
'linkURL2v': r'[`\g<link>`](\g<url>)',
'linkURL3v': r'[`\g<link>`](\g<url>)',
'plainURL': r'<\g<url>>',
# "Reference links" in pandoc are not yet supported
'title': r'% \g<subst>',
'author': pandoc_author,
'date': '% \g<subst>\n',
'chapter': lambda m: r'\g<subst>\n%s' % ('%'*len(m.group('subst').decode('utf-8'))),
'section': lambda m: r'\g<subst>\n%s' % ('='*len(m.group('subst').decode('utf-8'))),
'subsection': lambda m: r'\g<subst>\n%s' % ('-'*len(m.group('subst').decode('utf-8'))),
'subsubsection': lambda m: r'\g<subst>\n%s' % ('~'*len(m.group('subst').decode('utf-8'))),
'paragraph': r'*\g<subst>* ', # extra blank
'abstract': r'*\g<type>.* \g<text>\n\n\g<rest>'
}
CODE['pandoc'] = pandoc_code
from common import DEFAULT_ARGLIST
ARGLIST['pandoc'] = DEFAULT_ARGLIST
LIST['pandoc'] = {
'itemize':
{'begin': '', 'item': '*', 'end': '\n'},
'enumerate':
{'begin': '', 'item': '%d.', 'end': '\n'},
'description':
{'begin': '', 'item': '%s\n : ', 'end': '\n'},
'separator': '\n',
}
CROSS_REFS['pandoc'] = pandoc_ref_and_label
TABLE['pandoc'] = pandoc_table
INDEX_BIB['pandoc'] = pandoc_index_bib
EXERCISE['pandoc'] = plain_exercise
# no return, rely on in-place modification of dictionaries
|