Git-Mirrors/textfiles-politics
1
0
Fork 0
mirror of https://github.com/nhammer514/textfiles-politics.git synced 2025-02-25 17:11:16 -05:00
Code Issues Packages Projects Releases Wiki Activity

redirecting filepaths in personTagger.py

Browse Source
This commit is contained in:
ebeshero 2023-04-28 01:40:42 -04:00
parent c4ad94695b
commit cb909e97f3
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pythonCode/personTagger.py
View File

@ -1523,7 +1523,7 @@ ruler.add_patterns(patterns)
workingDir = os.getcwd() workingDir = os.getcwd()
CollPath = os.path.join(workingDir, '../pre-src-xml') CollPath = os.path.join(workingDir, '../pre-src-xml')
outputPath = os.path.join(workingDir, 'personTestingOutput/') outputPath = os.path.join(workingDir, '../src-xml')
# Everything in original conspiracy directory. # Everything in original conspiracy directory.
insideDir = os.listdir(CollPath) insideDir = os.listdir(CollPath)
print(insideDir) print(insideDir)
@ -1628,7 +1628,6 @@ def checkTags(file):
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine) newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine) newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine) newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"<name type='\w+?'>(\w+?)</name>(\w+)", r"\1\2", newLine)
# ebb: I'm repeating the above just in case of the weird event of triple or quadruple nested <ent> tags in <ent> tags. # ebb: I'm repeating the above just in case of the weird event of triple or quadruple nested <ent> tags in <ent> tags.
# We saw it happen on the LOTR project and running it through multiple passes of the above line ultimately got rid of them all # We saw it happen on the LOTR project and running it through multiple passes of the above line ultimately got rid of them all
# preserving only the outermost tags. # preserving only the outermost tags.