py/ai-job-search
1
0
Fork 0
mirror of https://github.com/MadsLorentzen/ai-job-search.git synced 2026-09-17 00:26:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix salary tool edge cases (#75)

Browse Source 
* fix: handle salary tool edge cases

* fix: preserve Danish salary compounds
This commit is contained in:
Kushida
2026-07-08 21:12:36 +02:00
committed by GitHub
parent d4415dff16
commit 9e26de2c67
4 changed files with 68 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/convert_salary_excel.py
+5 -8
View File
@@ -42,6 +42,7 @@ COMPANY_PATTERNS = {"firma", "company", "virksomhed", "employer", "arbejdsgiver"
CITY_PATTERNS = {"by", "city", "kommune", "location", "lokation", "sted"}
COUNT_PATTERNS = {"antal", "count", "number", "n", "employees", "medarbejdere"}
INDEX_PATTERNS = {"indeks", "index", "idx", "salary", "løn", "median", "average", "gennemsnit"}
DANISH_COMPOUND_PATTERNS = {"antal", "indeks", "løn", "gennemsnit", "medarbejdere"}
def header_matches(header, patterns):
@@ -50,10 +51,9 @@ def header_matches(header, patterns):
tokens = set(re.findall(r"[a-zæøåöäü0-9]+", h))
for p in patterns:
if len(p) == 1:
if p in tokens:
return True
elif p in h:
if p in tokens:
return True
if p in DANISH_COMPOUND_PATTERNS and p in h:
return True
return False
@@ -62,10 +62,7 @@ def strip_type_patterns(header, patterns):
"""Remove count/index words from a header to derive a category name."""
name = header.lower()
for p in patterns:
if len(p) == 1:
name = re.sub(rf"\b{re.escape(p)}\b", "", name)
else:
name = name.replace(p, "")
name = re.sub(rf"(?<![a-zæøåöäü0-9]){re.escape(p)}(?![a-zæøåöäü0-9])", "", name)
return name.strip(" _-")