flyingscorpio/flytex2html
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Now that \gls and \acr parsing is (more) functional, no need to handle the tags during dict creation

Browse source
This commit is contained in:
flyingscorpio@arch-desktop 2021-08-27 15:00:28 +02:00
parent b3aa98132d
commit 36d1cf9c93
2 changed files with 13 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.talismanrc
View file

@ -1,6 +1,6 @@
fileignoreconfig:
- filename: src/flytex2html.py
checksum: 7acbf2bba73f07f2ecec477fe5b102fbb96147964b056d5233a79c55788c21a1
checksum: 91f55dfaea9cc1358f01bf0aa4927e5df82e585e42f10429df8696a04a589737
- filename: src/tests/test_environments.py
ignore_detectors:
- filename

33
src/flytex2html.py
View file

@ -141,6 +141,14 @@ class Converter:
content = self.replace_acronyms(content)
content = self.replace_glossary_entries(content)
acronym[attribute] = content
for entry in self.glossary.values():
for attribute, content in entry.items():
content = self.replace_acronyms(content)
content = self.replace_glossary_entries(content)
if attribute != "description":
# remove link, should only be contained in description
content = re.sub(r"<a href=\".*?\">(.*?)</a>", r"\1", content)
entry[attribute] = content
self.latex_content = self.replace_acronyms(self.latex_content)
self.latex_content = self.replace_glossary_entries(self.latex_content)
@ -334,8 +342,6 @@ class Converter:
for entry, content in re.findall(
newglossary_pattern, extracted_glossaryentry, flags=re.DOTALL
):
content = self.replace_acronyms(content)
content = self.replace_glossary_entries(content, ignore_missing_keys=True)
entry_content = self._parse_gls_content(content)
glossary[entry] = {
"name": entry_content["name"],
@ -372,14 +378,12 @@ class Converter:
)
if not extracted_dualentry:
break
extracted_dualentry = self.replace_acronyms(extracted_dualentry)
extracted_dualentry = self.replace_glossary_entries(extracted_dualentry, ignore_missing_keys=True)
glossary = {
entry: {
"name": name,
"text": name,
"description": "\n".join(
self.replace_acronyms(line).strip()
line.strip()
for line in description.splitlines()
if line.strip()
),
@ -706,9 +710,7 @@ class Converter:
return latex_string
def replace_glossary_entries(
self, latex_string: str, ignore_missing_keys: bool = False
) -> str:
def replace_glossary_entries(self, latex_string: str) -> str:
"""Replace \\gls, \\Gls, \\glspl, \\Glspl, \\glssymbol and \\glsdesc.
Return the updated string.
@ -725,12 +727,7 @@ class Converter:
try:
found_entry = self.glossary[entry]
except KeyError:
try:
found_entry = self.acronyms[entry]
except KeyError as error:
if ignore_missing_keys:
continue
raise KeyError from error
found_entry = self.acronyms[entry]
regex = match.string[match.start() : match.end()]
if regex.lower().startswith(r"\glsdesc"):
@ -1397,7 +1394,6 @@ class Converter:
verbose(" - parsing content of glossary entry...")
pattern = r"(?:\n* *)?(\w+)=\{?(.*?)(?:\}|,)(?:\n* *)?"
href_pattern = r"<a href=\".*?\">(.*?)</a>"
entry_content = {
"name": "",
@ -1416,12 +1412,7 @@ class Converter:
remove_extracted=False,
)
content = content.replace(tag, "")
tag = tag.replace(f"{key}=", "")[:-1]
tag = tag.lstrip("{")
# for some keys, remove link, should not be contained in key
if key != "description":
tag = re.sub(href_pattern, r"\1", tag)
entry_content[key] = tag
entry_content[key] = tag.replace(f"{key}=", "")[:-1].lstrip("{")
for key, value in re.findall(pattern, content, flags=re.DOTALL):
if key not in entry_content.keys():