Mercurial > dottes

comparison abcfield.py @ 735:68f926e61d16

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Revise Markdown handling of character entities. Ideally I'd like the ABC character entities to survive Markdown and then get converted. But because they start with '\', they don't. So I have no alternative but to convert them to HTML entities, which Markdown then converts to UTF-8.
author Jim Hague <jim.hague@acm.org>
date Thu, 12 Oct 2017 13:32:24 +0100
parents e896cf93fe98
children 6bd946700312
comparison
equal deleted inserted replaced
734:e896cf93fe98 735:68f926e61d16
176 res = re.sub(r'href="(.*?).abc"', r'href="\1.html"', res) 176 res = re.sub(r'href="(.*?).abc"', r'href="\1.html"', res)
177 return res.strip() 177 return res.strip()
178 178
179 # Implement a custom Markdown shorthand for referencing ABC files. 179 # Implement a custom Markdown shorthand for referencing ABC files.
180 # <foo.abc> will expand to ['title of foo'](foo.abc). 180 # <foo.abc> will expand to ['title of foo'](foo.abc).
181 def expandCustomMarkdown(t, dir, latex): 181 def expandCustomMarkdown(t, dir):
182 # Given a match to (foo.abc), return a markdown link to the tune with the 182 # Given a match to (foo.abc), return a markdown link to the tune with the
183 # title (and subtitle, if present) of the tune as the text of the link. 183 # title (and subtitle, if present) of the tune as the text of the link.
184 # Because we're going through Markdown, character entities must be
185 # HTML. Pandoc will convert them to UTF-8.
184 def getTitleLink(m): 186 def getTitleLink(m):
185 fname = m.group(1) + ".abc" 187 fname = m.group(1) + ".abc"
186 path = pathlib.Path(dir, fname) 188 path = pathlib.Path(dir, fname)
187 with path.open() as f: 189 with path.open() as f:
188 lines = f.readlines() 190 lines = f.readlines()
189 return "[" + getFullTitle(lines, dir, latex=latex) + "](" + fname + ")" 191 return "[" + getFullTitle(lines, dir) + "](" + fname + ")"
190 return re.sub(r'<(.*?).abc>', getTitleLink, t) 192 return re.sub(r'<(.*?).abc>', getTitleLink, t)
191 193
192 # Return the raw text for a given field. Optionally the nth field is taken, 194 # Return the raw text for a given field. Optionally the nth field is taken,
193 # or the field data must start with a designated string to be recognised. 195 # or the field data must start with a designated string to be recognised.
194 def getFieldText(lines, field, n = 1, starts = None): 196 def getFieldText(lines, field, n = 1, starts = None):
221 223
222 # Return display text for a given field. 224 # Return display text for a given field.
223 def getFieldDisplayText(lines, dir, field, n = 1, starts = None, latex = False): 225 def getFieldDisplayText(lines, dir, field, n = 1, starts = None, latex = False):
224 res = getFieldText(lines, field, n, starts) 226 res = getFieldText(lines, field, n, starts)
225 if res: 227 if res:
226 res = convertAccents(res, latex) 228 # Fields that go through Markdown must have HTML entities.
229 mdfield = field.upper() in ['H', 'N'];
230 res = convertAccents(res, False if mdfield else latex)
227 if field.upper() == "T": 231 if field.upper() == "T":
228 res = convertTitleToDisplay(res) 232 res = convertTitleToDisplay(res)
229 elif field.upper() == "K": 233 elif field.upper() == "K":
230 res = convertKeyToDisplay(res) 234 res = convertKeyToDisplay(res)
231 elif field.upper() in ["H", "N"]: 235 elif mdfield:
232 res = convertMarkdown(expandCustomMarkdown(res, dir, latex), latex) 236 res = convertMarkdown(expandCustomMarkdown(res, dir), latex)
233 return res 237 return res
234 238
235 # Return full title (title + [" (" + subtitle + ")"] if subtitle exists). 239 # Return full title (title + [" (" + subtitle + ")"] if subtitle exists).
236 def getFullTitle(lines, dir, starts = None, latex = False): 240 def getFullTitle(lines, dir, starts = None, latex = False):
237 title = getFieldDisplayText(lines, dir, "T", starts=starts, latex=latex) 241 title = getFieldDisplayText(lines, dir, "T", starts=starts, latex=latex)