def extractFromJob(self, node, fieldNode):
for start, end in fieldNode.getExperienceIndex().items():
for line in self.content[start : end]:
if 'work experience' == line:#don't process work experience, only process experience
break
wordsInList = word_tokenize(line)
for word in wordsInList:
if word in self.getExperienceKeywordList():# to tackle solely requirements section as there can be a mixture of key requirements and skills section
self.extractedContent.add(line)
for line in self.extractedContent:
wordsInList = word_tokenize(line)
try:
annotatedList = [i.get('surfaceForm') for i in annotate(line)]
yearIndex = None
year = 'year'
years = 'years'
if years in wordsInList or year in wordsInList:
yearIndex = wordsInList.index(years) or wordsInList.index(year)
for word in annotatedList:
if yearIndex is not None and word[0].isalpha():
experienceSubNode = ExperienceSubNode(word, " ".join(wordsInList[yearIndex-1 : yearIndex+1]))
node.addExperience(experienceSubNode)
else:
if word[0].isalpha():
experienceSubNode = ExperienceSubNode(word, None)
node.addExperience(experienceSubNode)
except:
pass
def parse(self, node, fieldNode):
if bool(fieldNode.getSkillsIndex()):
for start, end in fieldNode.getSkillsIndex().items():
for line in self.content[start : end]:
if line and 'page' not in line:
self.extractedContent.add(line)
listString = "\n".join(line for line in self.extractedContent)
self.extractedContent = [i.get('surfaceForm') for i in annotate(listString)]
for line in self.extractedContent:
if line not in self.getSkillKeywordList():
node.addSkill(line)
def parse(self, node, fieldNode):
if bool(fieldNode.getLanguageIndex()):
for start, end in fieldNode.getLanguageIndex().items():
for line in self.content[start : end]:
self.extractedContent.add(line)
listString = "\n".join(line for line in self.extractedContent)
if len(self.extractedContent) > 0:
self.extractedContent = annotate(listString)
for line in self.extractedContent:
if line.get('surfaceForm') not in self.getLanguageKeywordsList() and 'language' in line.get('types').lower():
node.addLanguage(line.get('surfaceForm'))
def parse(self, node, fieldNode):
if bool(fieldNode.getSkillsIndex()):
for start, end in fieldNode.getSkillsIndex().items():
for line in self.content[start:end]:
if line and 'page' not in line:
self.extractedContent.add(line)
listString = "\n".join(line for line in self.extractedContent)
self.extractedContent = [
i.get('surfaceForm') for i in annotate(listString)
]
for line in self.extractedContent:
if line not in self.getSkillKeywordList():
node.addSkill(line)
def parse(self, node, fieldNode):
if bool(fieldNode.getLanguageIndex()):
for start, end in fieldNode.getLanguageIndex().items():
for line in self.content[start:end]:
self.extractedContent.add(line)
listString = "\n".join(line for line in self.extractedContent)
if len(self.extractedContent) > 0:
self.extractedContent = annotate(listString)
for line in self.extractedContent:
if line.get(
'surfaceForm') not in self.getLanguageKeywordsList(
) and 'language' in line.get('types').lower():
node.addLanguage(line.get('surfaceForm'))
def extractEducationFromJob(self, node, fieldNode):
for start, end in fieldNode.getEducationIndex().items():
for line in self.content[start : end]:
wordsList = word_tokenize(line)
if len(wordsList) > 0:
for word in wordsList:
if word in self.getEducationLevel():
self.extractedContent.add(line)
listString = "\n".join(line for line in self.extractedContent)
try:
self.extractedContent = [i.get('surfaceForm') for i in annotate(listString)]
for line in self.extractedContent:
if line in self.getEducationLevel() and line not in self.getIgnoredKeywords():
educationType = line
if line not in self.getEducationLevel() and line not in self.getIgnoredKeywords():
node.addEducation(educationType +" in "+ line, None)
except:
pass
