def extract_traininfo(text):
train = resume_struct.get_training_struct()
for line in text.split('\n'):
m_train = re.search(train_reg, line)
if m_train:
timestamp = match_timestamp.match_timestamp_by_reg(train_reg, line)
train["start_time"], train["end_time"], train[
"so_far"] = StringUtils.transform_timestamp(timestamp)
train["name"] = m_train.group("train").strip()
if len(train["name"].split("\t")) == 2:
train["authority"] = train["name"].split("\t")[0]
train["name"] = train["name"].split("\t")[1]
mauth = re.search(u"^培训机构：(.+)", line)
if mauth:
train["authority"] = mauth.group(1).strip()
mcity = re.search(u"^培训地点：(.+)", line)
if mcity:
train["city"] = mcity.group(1).strip()
mdesc = re.search(u"^培训描述：(.+)", line)
if mdesc:
train["description"] = mdesc.group(1).strip()
return train
def extract_projectinfo(text):
project = resume_struct.get_project_struct()
project["ori_text"] = text
lines = text.split("\n")
isDesc, isResp = False, False
for preline, line in izip([""] + lines, lines):
m_proj = re.search(project_reg, line)
if m_proj:
timestamp = match_timestamp.match_timestamp_by_reg(
project_reg, line)
project["name"] = m_proj.group("project").strip()
project["start_time"], project["end_time"], project[
"so_far"] = StringUtils.transform_timestamp(timestamp)
m_desc = re.search(u"项目描述(:|：)", line)
if m_desc:
line = re.sub(u"项目描述(:|：)", "", line).strip()
isDesc, isResp = True, False
m_resp = re.search(u"责任描述(:|：)", line)
if m_resp:
line = re.sub(u"责任描述(:|：)", "", line).strip()
isDesc, isResp = False, True
pass
if isDesc:
project["describe"] += '\n' + line if project[
"describe"] and line else line
if isResp:
project["responsibilities"] += '\n' + line if project[
"responsibilities"] and line else line
return project
def extract_certinfo(text):
cert = resume_struct.get_certificate_struct()
for line in text.split('\n'):
m_cert = re.search(certi_reg, line)
if m_cert:
timestamp = match_timestamp.match_timestamp_by_reg(certi_reg, line)
cert["name"] = m_cert.group("name").strip()
cert["start_time"], _, _ = StringUtils.transform_timestamp(
timestamp)
return cert
def extract_eduinfo(expblock):
edu = resume_struct.get_education_struct()
edu["ori_text"] = expblock
for line in expblock.split("\n"):
m = re.search(edu_reg, line)
if m:
timestamp = match_timestamp.match_timestamp_by_reg(edu_reg, line)
edu["school_name"] = m.group("school").strip()
edu["start_time"], edu["end_time"], edu[
"so_far"] = StringUtils.transform_timestamp(timestamp)
edu["degree"] = match_education.match_degree(m.group('degree'), 99)
edu["discipline_name"] = m.group('discipline').strip()
return edu
def extract_projectinfo(text):
project = resume_struct.get_project_struct()
project["ori_text"] = text
time_found = False
isResp, isDesc, isAchi = False, False, False
for line in text.split('\n'):
m_proj = re.search(project_reg, line)
if m_proj:
timestamp = match_timestamp.match_timestamp_by_reg(
project_reg, line)
project["start_time"], project["end_time"], project[
"so_far"] = StringUtils.transform_timestamp(timestamp)
time_found = True
continue
if time_found:
project["name"], time_found = line, False
continue
m_posi = re.search(u"项目职务(:|：)\s*(?P<posi>.+)", line)
if m_posi:
project["position_name"] = m_posi.group("posi")
m_corp = re.search(u"所在公司(:|：)(?P<corp>.+)", line)
if m_corp:
project["corporation_name"] = m_corp.group("corp")
m_desc = re.search(u"项目简介(:|：)", line)
if m_desc:
line = re.sub(u"项目简介(:|：)", "", line).strip()
isResp, isDesc, isAchi = False, True, False
m_resp = re.search(u"项目职责(:|：)", line)
if m_resp:
line = re.sub(u"项目职责(:|：)", "", line).strip()
isResp, isDesc, isAchi = True, False, False
m_achi = re.search(u"项目业绩(:|：)", line)
if m_achi:
line = re.sub(u"项目业绩(:|：)", "", line).strip()
isResp, isDesc, isAchi = False, False, True
pass
if isDesc:
project["describe"] += '\n' + line if project[
"describe"] and line else line
if isResp:
project["responsibilities"] += '\n' + line if project[
"responsibilities"] and line else line
if isAchi:
project["achivement"] += "\n" + line if project[
"achivement"] and line else line
pass
return project
def extract_eduinfo(expblock):
edu = resume_struct.get_education_struct()
edu["ori_text"] = expblock
for line in expblock.split("\n"):
m = re.search(edu_reg, line)
if m:
edu["school_name"] = m.group("school").strip()
edu["discipline_name"] = m.group("disc").strip()
edu["degree"] = match_education.match_degree(
m.group("degree").strip(), 99)
timestamp = match_timestamp.match_timestamp_by_reg(edu_reg, line)
edu["start_time"], edu["end_time"], edu[
"so_far"] = StringUtils.transform_timestamp(timestamp)
else:
edu["discipline_desc"] += "\n" + line.strip(
) if edu["discipline_desc"] else line.strip()
edu["discipline_desc"] = re.sub(u"^专业描述(：|:)", "",
edu["discipline_desc"]).strip()
return edu
def extract_workinfo(text):
work = resume_struct.get_emplyment_struct()
work["ori_text"] = text
last_line, isResp = "", False
for line in text.split('\n'):
m_time = re.search(work_reg, line)
if m_time:
timestamp = match_timestamp.match_timestamp_by_reg(work_reg, line)
work["start_time"], work["end_time"], work[
"so_far"] = StringUtils.transform_timestamp(timestamp)
last_line = "time"
continue
if last_line == "time":
work["corporation_name"] = line
last_line = "corp_name"
continue
if last_line == "corp_name":
work["position_name"] = line
last_line = ""
continue
m_loc = re.search(u"所在地区(：|:)(?P<loc>.+)", line)
if m_loc:
work["city"] = m_loc.group("loc")
m_resp = re.search(u"职责业绩(：|:)", line)
if m_resp:
line = re.sub(u".*职责业绩(：|:)", "", line)
isResp = True
if isResp:
work["responsibilities"] += "\n" + line if work[
"responsibilities"] and line else line
pass
work["responsibilities"] = re.sub(u"^工作描述(:|：)", "",
work["responsibilities"]).strip()
return work
def extract_workinfo(text):
work = resume_struct.get_emplyment_struct()
work["ori_text"] = text
lastline = "not found company"
for line in text.split('\n'):
if re.search(u"工作描述(:|：)", line):
lastline = "position"
if lastline == "not found company":
m_company = re.search(work_reg, line)
if m_company:
timestamp = match_timestamp.match_timestamp_by_reg(
work_reg, line)
work["corporation_name"] = clean_company_name(
m_company.group("company").strip())
work["start_time"], work["end_time"], work[
"so_far"] = StringUtils.transform_timestamp(timestamp)
lastline = "company name"
pass
elif lastline == "company name":
items = line.split("|")
if len(items) > 0:
work["industry_name"] = items[0].strip()
lastline = "industry"
continue
elif lastline == "industry":
items = re.split("\s+", line)
if len(items) > 1:
work["architecture_name"] = items[0]
work["position_name"] = items[1]
lastline = "position"
elif lastline == "position":
work["responsibilities"] += '\n' + line if work[
"responsibilities"] else line
pass
work["responsibilities"] = re.sub(u"^工作描述(:|：)", "",
work["responsibilities"]).strip()
return work
def extract_workinfo(text):
work = resume_struct.get_emplyment_struct()
work["ori_text"] = text
last_industry = False
for line in text.split('\n'):
m_company = re.search(work_reg, line)
if m_company:
timestamp = match_timestamp.match_timestamp_by_reg(work_reg, line)
work["corporation_name"] = m_company.group("company").strip()
work["corporation_name"] = clean_company_name(
work["corporation_name"])
work["start_time"], work["end_time"], work[
"so_far"] = StringUtils.transform_timestamp(timestamp)
m_position = re.search(u"职位名称(：|:)(?P<pos>.+)部门(：|:)(?P<arc>.+)", line)
if m_position:
work["position_name"] = m_position.group("pos").replace(
u"(兼职)", "").strip()
work["architecture_name"] = m_position.group("arc")
m_industry = re.search(u"(行业|所属行业)(：|:)\s*(?P<ind>.+?)(\s|$)", line)
if m_industry:
work["industry_name"] = m_industry.group("ind").strip()
last_industry = True
continue
if not work["position_name"] and last_industry:
if len(line.split("\t")) == 2:
work["architecture_name"] = line.split("\t")[0].strip()
work["position_name"] = line.split("\t")[1].strip()
if len(line.split("\t")) == 1:
work["position_name"] = line.split("\t")[0].strip()
continue
if last_industry:
work["responsibilities"] += "\n" + line if work[
"responsibilities"] else line
pass
work["responsibilities"] = re.sub(u"^工作描述(:|：)", "",
work["responsibilities"]).strip()
return work
def extract_eduinfo(expblock):
edu = resume_struct.get_education_struct()
edu["ori_text"] = expblock
lastline = "not found school"
for line in expblock.split("\n"):
if lastline == "not found school":
m = re.search(edu_reg, line)
if m:
timestamp = match_timestamp.match_timestamp_by_reg(
edu_reg, line)
edu["school_name"] = re.sub(u"海外经历", "",
m.group("school")).strip()
edu["start_time"], edu["end_time"], edu[
"so_far"] = StringUtils.transform_timestamp(timestamp)
lastline = "school"
elif lastline == "school":
items = line.split("|")
if len(items) >= 2:
edu["degree"] = match_education.match_degree(items[0], 99)
edu["degree_ori"] = items[0].strip()
edu["discipline_name"] = items[1].strip()
else:
if match_education.match_degree(items):
edu["degree"] = match_education.match_degree(items[0])
edu["degree_ori"] = items[0].strip()
else:
edu["discipline_name"] = items[0].strip()
lastline = "degree"
elif lastline == "degree":
edu["discipline_desc"] += '\n' + line.strip(
) if edu["discipline_desc"] else line.strip()
pass
pass
edu["discipline_desc"] = re.sub(u"^专业描述(：|:)", "",
edu["discipline_desc"]).strip()
return edu
def extract_eduinfo(expblock):
edu = resume_struct.get_education_struct()
edu["ori_text"] = expblock
time_found = False
for line in expblock.split("\n"):
m_time = re.search(edu_reg, line)
if m_time:
timestamp = match_timestamp.match_timestamp_by_reg(edu_reg, line)
edu["start_time"], edu["end_time"], edu[
"so_far"] = StringUtils.transform_timestamp(timestamp)
time_found = True
continue
if time_found:
edu["school_name"] = line.strip()
time_found = False
m_dis = re.search(u"专业(:|：)(?P<dis>.+)", line)
if m_dis:
edu["discipline_name"] = m_dis.group("dis").strip()
m_deg = re.search(u"学历(:|：)(?P<deg>.+)", line)
if m_deg:
edu["degree"] = match_education.match_degree(
m_deg.group("deg").strip())
return edu
def extract_projectinfo(text):
project = resume_struct.get_project_struct()
project["ori_text"] = text
lastline = "not found project"
isResp, isDesc = False, False
for line in text.split('\n'):
if lastline == "not found project":
m_proj = re.search(project_reg, line)
if m_proj:
timestamp = match_timestamp.match_timestamp_by_reg(
project_reg, line)
project["name"] = m_proj.group("project").strip()
project["name"] = re.sub(u"已关联$", "", project["name"]).strip()
project["start_time"], project["end_time"], project[
"so_far"] = StringUtils.transform_timestamp(timestamp)
lastline = "project"
pass
elif lastline == "project":
m_desc = re.search(u"项目描述(:|：)", line)
if m_desc:
line = re.sub(u"项目描述(:|：)", "", line).strip()
isDesc, isResp = True, False
m_resp = re.search(u"责任描述(:|：)", line)
if m_resp:
line = re.sub(u"责任描述(:|：)", "", line).strip()
isDesc, isResp = False, True
pass
if isDesc:
project[
"describe"] += '\n' + line if project["describe"] else line
if isResp:
project["responsibilities"] += '\n' + line if project[
"responsibilities"] else line
pass
return project
