Last active
December 2, 2019 05:18
-
-
Save mgd020/854fab4c96a66ef63c5197528b017391 to your computer and use it in GitHub Desktop.
Parse an XML snippet with regular expressions only.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
from xml.sax.saxutils import unescape | |
tags_pattern = re.compile(r"</(?P<close>\S+)>|<(?P<open>[^>!?/\s]+)(\s+(?P<attrs>.*?))?(?P<empty>/)?\s*>|<!--(?P<comment>.*?)-->|(?P<cdata><!\[CDATA\[)") | |
attrs_pattern = re.compile(r"\s*(?P<name>\S+)\s*=\s*(?P<quote>\"|')(?P<value>.*?)(?P=quote)") | |
cdata_close_pattern = re.compile(r"\]\]>") | |
escaped_entities = {""": '"', "'": "'"} | |
def xml_sax_parse_string(string): | |
start = 0 | |
for match in iter(lambda: tags_pattern.search(string, start), None): | |
if start and match.start() != start: | |
yield "characters", unescape(string[start:match.start()], escaped_entities) | |
if match.group("cdata") is not None: | |
start = match.end() | |
match = cdata_close_pattern.search(string, start) | |
if match is None: | |
break | |
yield "characters", unescape(string[start:match.start()], escaped_entities) | |
elif match.group("open") is not None: | |
attrs = { | |
name: unescape(value, escaped_entities) | |
for name, _, value in attrs_pattern.findall(match.group("attrs") or "") | |
} | |
yield "startElement", match.group("open"), attrs | |
if match.group("empty"): | |
yield "endElement", match.group("open") | |
elif match.group("close") is not None: | |
yield "endElement", match.group("close") | |
start = match.end() | |
if start < len(string) - 1: | |
yield "characters", unescape(string[start:], escaped_entities) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment