Mercurial > dottes

changeset 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 4a4d39bcc145
files abcfield.py
diffstat 1 files changed, 9 insertions(+), 5 deletions(-) [+]
line wrap: on
line diff
--- a/abcfield.py	Thu Oct 12 13:29:50 2017 +0100
+++ b/abcfield.py	Thu Oct 12 13:32:24 2017 +0100
@@ -178,15 +178,17 @@
 
 # Implement a custom Markdown shorthand for referencing ABC files.
 # <foo.abc> will expand to ['title of foo'](foo.abc).
-def expandCustomMarkdown(t, dir, latex):
+def expandCustomMarkdown(t, dir):
     # Given a match to (foo.abc), return a markdown link to the tune with the
     # title (and subtitle, if present) of the tune as the text of the link.
+    # Because we're going through Markdown, character entities must be
+    # HTML. Pandoc will convert them to UTF-8.
     def getTitleLink(m):
         fname = m.group(1) + ".abc"
         path = pathlib.Path(dir, fname)
         with path.open() as f:
             lines = f.readlines()
-            return "[" + getFullTitle(lines, dir, latex=latex) + "](" + fname + ")"
+            return "[" + getFullTitle(lines, dir) + "](" + fname + ")"
     return re.sub(r'<(.*?).abc>', getTitleLink, t)
 
 # Return the raw text for a given field. Optionally the nth field is taken,
@@ -223,13 +225,15 @@
 def getFieldDisplayText(lines, dir, field, n = 1, starts = None, latex = False):
     res = getFieldText(lines, field, n, starts)
     if res:
-        res = convertAccents(res, latex)
+        # Fields that go through Markdown must have HTML entities.
+        mdfield = field.upper() in ['H', 'N'];
+        res = convertAccents(res, False if mdfield else latex)
         if field.upper() == "T":
             res = convertTitleToDisplay(res)
         elif field.upper() == "K":
             res = convertKeyToDisplay(res)
-        elif field.upper() in ["H", "N"]:
-            res = convertMarkdown(expandCustomMarkdown(res, dir, latex), latex)
+        elif mdfield:
+            res = convertMarkdown(expandCustomMarkdown(res, dir), latex)
     return res
 
 # Return full title (title + [" (" + subtitle + ")"] if subtitle exists).