real_tabasco_sauce/0ad
1
0
Fork 0
forked from 0ad/0ad
Code Pull Requests Actions Activity

Simplify XML parsing by iterating only once

Browse Source 
This simplifies the XML parsing, by iterating over the DOM tree only
once. Curiously this doesn't result in significant performance gains.

As the keywords are now found in the order they appear in the
document instead of the order they are mentioned in messages.json, the
order of a few strings in the PO-templates changes caused by the changes
in this commit.
This commit is contained in:
Dunedan 2024-09-07 06:38:54 +02:00
parent eeb502c115
commit 0e84957979
Signed by untrusted user: Dunedan
GPG Key ID: 885B16854284E0B2
1 changed files with 36 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
source/tools/i18n/i18n_helper/extractors.py
View File

@ -452,38 +452,40 @@ class XmlExtractor(Extractor):
def extract_from_file(self, filepath):
with open(filepath, encoding="utf-8-sig") as file_object:
xml_document = etree.parse(file_object)
for keyword in self.keywords:
for element in xml_document.iter(keyword):
lineno = element.sourceline
if element.text is None:
continue
comments = []
if "extractJson" in self.keywords[keyword]:
json_extractor = self.get_json_extractor()
json_extractor.set_options(self.keywords[keyword]["extractJson"])
for message, context in json_extractor.extract_from_string(element.text):
yield message, None, context, lineno, comments
else:
context = None
if "context" in element.attrib:
context = str(element.get("context"))
elif "tagAsContext" in self.keywords[keyword]:
context = keyword
elif "customContext" in self.keywords[keyword]:
context = self.keywords[keyword]["customContext"]
if "comment" in element.attrib:
comment = element.get("comment")
comment = " ".join(
comment.split()
) # Remove tabs, line breaks and unecessary spaces.
comments.append(comment)
if "splitOnWhitespace" in self.keywords[keyword]:
for split_text in element.text.split():
# split on whitespace is used for token lists, there, a
# leading '-' means the token has to be removed, so it's not
# to be processed here either
if split_text[0] != "-":
yield str(split_text), None, context, lineno, comments
else:
yield str(element.text), None, context, lineno, comments
for element in xml_document.iter(*self.keywords.keys()):
keyword = element.tag
lineno = element.sourceline
if element.text is None:
continue
comments = []
if "extractJson" in self.keywords[keyword]:
json_extractor = self.get_json_extractor()
json_extractor.set_options(self.keywords[keyword]["extractJson"])
for message, context in json_extractor.extract_from_string(element.text):
yield message, None, context, lineno, comments
else:
context = None
if "context" in element.attrib:
context = str(element.get("context"))
elif "tagAsContext" in self.keywords[keyword]:
context = keyword
elif "customContext" in self.keywords[keyword]:
context = self.keywords[keyword]["customContext"]
if "comment" in element.attrib:
comment = element.get("comment")
comment = " ".join(
comment.split()
) # Remove tabs, line breaks and unnecessary spaces.
comments.append(comment)
if "splitOnWhitespace" in self.keywords[keyword]:
for split_text in element.text.split():
# split on whitespace is used for token lists, there, a
# leading '-' means the token has to be removed, so it's not
# to be processed here either
if split_text[0] != "-":
yield str(split_text), None, context, lineno, comments
else:
yield str(element.text), None, context, lineno, comments