pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix errors detected by Ruff (#3918)

Browse Source 
### What problem does this PR solve?

Fix errors detected by Ruff

### Type of change

- [x] Refactoring
This commit is contained in:
Zhichang Yu
2024-12-08 14:21:12 +08:00
committed by GitHub
parent e267a026f3
commit 0d68a6cd1b
97 changed files with 2558 additions and 1976 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
deepdoc/parser/resume/__init__.py
View File

@ -15,21 +15,42 @@ import datetime
def refactor(cv):
for n in ["raw_txt", "parser_name", "inference", "ori_text", "use_time", "time_stat"]:
if n in cv and cv[n] is not None: del cv[n]
for n in [
"raw_txt",
"parser_name",
"inference",
"ori_text",
"use_time",
"time_stat",
]:
if n in cv and cv[n] is not None:
del cv[n]
cv["is_deleted"] = 0
if "basic" not in cv: cv["basic"] = {}
if cv["basic"].get("photo2"): del cv["basic"]["photo2"]
if "basic" not in cv:
cv["basic"] = {}
if cv["basic"].get("photo2"):
del cv["basic"]["photo2"]
for n in ["education", "work", "certificate", "project", "language", "skill", "training"]:
if n not in cv or cv[n] is None: continue
if type(cv[n]) == type({}): cv[n] = [v for _, v in cv[n].items()]
if type(cv[n]) != type([]):
for n in [
"education",
"work",
"certificate",
"project",
"language",
"skill",
"training",
]:
if n not in cv or cv[n] is None:
continue
if isinstance(cv[n], dict):
cv[n] = [v for _, v in cv[n].items()]
if not isinstance(cv[n], list):
del cv[n]
continue
vv = []
for v in cv[n]:
if "external" in v and v["external"] is not None: del v["external"]
if "external" in v and v["external"] is not None:
del v["external"]
vv.append(v)
cv[n] = {str(i): vv[i] for i in range(len(vv))}
@ -42,24 +63,44 @@ def refactor(cv):
cv["basic"][t] = cv["basic"][n]
del cv["basic"][n]
work = sorted([v for _, v in cv.get("work", {}).items()], key=lambda x: x.get("start_time", ""))
edu = sorted([v for _, v in cv.get("education", {}).items()], key=lambda x: x.get("start_time", ""))
work = sorted(
[v for _, v in cv.get("work", {}).items()],
key=lambda x: x.get("start_time", ""),
)
edu = sorted(
[v for _, v in cv.get("education", {}).items()],
key=lambda x: x.get("start_time", ""),
)
if work:
cv["basic"]["work_start_time"] = work[0].get("start_time", "")
cv["basic"]["management_experience"] = 'Y' if any(
[w.get("management_experience", '') == 'Y' for w in work]) else 'N'
cv["basic"]["management_experience"] = (
"Y"
if any([w.get("management_experience", "") == "Y" for w in work])
else "N"
)
cv["basic"]["annual_salary"] = work[-1].get("annual_salary_from", "0")
for n in ["annual_salary_from", "annual_salary_to", "industry_name", "position_name", "responsibilities",
"corporation_type", "scale", "corporation_name"]:
for n in [
"annual_salary_from",
"annual_salary_to",
"industry_name",
"position_name",
"responsibilities",
"corporation_type",
"scale",
"corporation_name",
]:
cv["basic"][n] = work[-1].get(n, "")
if edu:
for n in ["school_name", "discipline_name"]:
if n in edu[-1]: cv["basic"][n] = edu[-1][n]
if n in edu[-1]:
cv["basic"][n] = edu[-1][n]
cv["basic"]["updated_at"] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
if "contact" not in cv: cv["contact"] = {}
if not cv["contact"].get("name"): cv["contact"]["name"] = cv["basic"].get("name", "")
return cv
if "contact" not in cv:
cv["contact"] = {}
if not cv["contact"].get("name"):
cv["contact"]["name"] = cv["basic"].get("name", "")
return cv