py/ai-job-search
1
0 Fork 0
mirror of https://github.com/MadsLorentzen/ai-job-search.git synced 2026-11-02 13:12:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(scrape): distinguish non-Latin companies in fallback job keys (#487)

Browse Source
This commit is contained in:
Ayobami Adegoke authored and GitHub committed 2026-09-21 08:24:15 +02:00
1 parent 6a308c5cc8
commit 456f2bfdbf
3 files changed
+42 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tools/job_key.py
+6 -1
View File
@@ -84,7 +84,12 @@ def _cap(slug: str, limit: int) -> str:
def make_key(company: str, title: str, url: str = "") -> str:
"""The canonical seen_jobs.json key for one posting."""
company_slug = _cap(slugify(company), COMPANY_MAX) or "unknown-company"
company_slug = _cap(slugify(company), COMPANY_MAX)
if not company_slug:
name = unicodedata.normalize("NFC", str(company or "").strip().casefold())
# An absent name stays unknown; a non-Latin name still has an identity.
digest = hashlib.sha1(name.encode("utf-8")).hexdigest()[:HASH_LEN]
company_slug = f"company-{digest}" if name else "unknown-company"
title_slug = _cap(slugify(title), TITLE_MAX)
if not title_slug:
# No Latin characters in the title. The portal's own numeric id is the