def CreateSupplementalSentenceStructures(supp_file_path):
"""
Create SentenceStructures from supplemental documents
:param supp_file_path: Path to directory where supplemental documents are located
:return: Dictionary of lists of SentenceStructure objects keyed on document name stripped of extension
"""
#Create a dictionary of documents
docDictionary = {}
# cd into test file directory
cwd = os.getcwd()
os.chdir(supp_file_path)
#Iterate over documents in the supp_file_path directory
for document in os.listdir():
#Instantiate a list to hold a SentenceStructure for each sentence(line) in the document
docSentenceStructureList = []
#Open the document
doc = open(document, "r")
docText = doc.read()
docTextProcessed = preprocess(docText)
docTextProcessedSplit = docTextProcessed.splitlines()
doc.close()
doc = open(document, "r")
#Strip the extension from the file to get the document name
docName = os.path.splitext(document)[0]
#Iterate over sentences in the document
counter = 0
for sentence in doc.readlines():
#Create a SentenceStructure obj
ss = SentenceStructure(sentence, docName)
ss.modifiedSentence = docTextProcessedSplit[counter]
#Add SentenceStructure obj to the list
docSentenceStructureList.append(ss)
counter += 1
#Add the SentenceStructureList to the dictionary
docDictionary[docName] = docSentenceStructureList
#Close the document
doc.close()
#Return to original path
os.chdir(cwd)
#Return the dictionary
return docDictionary
def CreateSentenceStructures(raw_file_path):
"""
Create SentenceStructures from raw documents
:param raw_file_path: Path to directory where raw documents are located
:return: Dictionary of lists of SentenceStructure objects keyed on document name stripped of extension
"""
#Create a dictionary of documents
docDictionary = {}
# cd into test file directory
cwd = os.getcwd()
os.chdir(raw_file_path)
#Iterate over documents in the raw_file_path directory
for document in os.listdir():
#Instantiate a list to hold a SentenceStructure for each sentence(line) in the document
docSentenceStructureList = []
#Open the document
doc = open(document, "r")
#Iterate over sentences in the document
for sentence in doc.readlines():
#Create a SentenceStructure obj
ss = SentenceStructure(sentence)
#Add SentenceStructure obj to the list
docSentenceStructureList.append(ss)
#Strip the extension from the file to get the document name
docName = os.path.splitext(document)[0]
#Add the SentenceStructureList to the dictionary
docDictionary[docName] = docSentenceStructureList
#Close the document
doc.close()
#Return to original path
os.chdir(cwd)
#Return the dictionary
return docDictionary
def create_sentence_structures(raw_file_path):
"""
Iterates through all documents in the directory specified in the params and creates a SentenceStructure object for each sentence.
:param raw_file_path: Path to directory where raw documents are located
:return: Dictionary of lists of SentenceStructure objects keyed on document name stripped of extension
"""
#Create a dictionary of documents
doc_dictionary = {}
max_sentence_length = 0
# cd into test file directory
cwd = os.getcwd()
os.chdir(raw_file_path)
#Iterate over documents in the raw_file_path directory
for document in os.listdir():
#Instantiate a list to hold a SentenceStructure for each sentence(line) in the document
doc_sentence_structure_list = []
#Open the document
doc = open(document, "r")
doc_text = doc.read()
doc_text_processed = preprocess(doc_text)
doc_text_processed_split = doc_text_processed.splitlines()
doc.close()
doc = open(document, "r")
try:
#Iterate over sentences in the document
counter = 0
for sentence in doc.readlines():
#Create a SentenceStructure obj
ss = SentenceStructure(sentence)
lower_sentence = sentence.lower()
ss.modified_sentence = lower_sentence
#TODO(Jeff) Readd Preprocessed text.
#ss.modified_sentence = doc_text_processed_split[counter]
if len(ss.original_sentence_array) > max_sentence_length:
max_sentence_length = len(ss.original_sentence_array)
#Add SentenceStructure obj to the list
doc_sentence_structure_list.append(ss)
counter += 1
except:
print("ERR. " + str(document))
sys.exit(0)
assert(len(doc_sentence_structure_list) == len(doc_text_processed_split)), "Assertion Failed, array lengths don't match. " + str(len(doc_sentence_structure_list)) + " " + str(len(doc_text_processed_split))
#Strip the extension from the file to get the document name
doc_name = os.path.splitext(document)[0]
#Add the SentenceStructureList to the dictionary
doc_dictionary[doc_name] = doc_sentence_structure_list
#Close the document
doc.close()
#Return to original path
os.chdir(cwd)
#Return the dictionary
return doc_dictionary, max_sentence_length
def CreateSentenceStructures(raw_file_path):
"""
Create SentenceStructures from raw documents
:param raw_file_path: Path to directory where raw documents are located
:return: Dictionary of lists of SentenceStructure objects keyed on document name stripped of extension
"""
#Create a dictionary of documents
docDictionary = {}
# cd into test file directory
cwd = os.getcwd()
os.chdir(raw_file_path)
#Iterate over documents in the raw_file_path directory
for document in os.listdir():
#Instantiate a list to hold a SentenceStructure for each sentence(line) in the document
docSentenceStructureList = []
#Open the document
doc = open(document, "r")
docText = doc.read()
docTextProcessed = preprocess(docText)
docTextProcessedSplit = docTextProcessed.splitlines()
doc.close()
doc = open(document, "r")
try:
#Iterate over sentences in the document
counter = 0
for sentence in doc.readlines():
#Create a SentenceStructure obj
ss = SentenceStructure(sentence)
ss.modifiedSentence = docTextProcessedSplit[counter]
#Add SentenceStructure obj to the list
docSentenceStructureList.append(ss)
counter += 1
except:
print("ERR. " + str(document))
sys.exit(0)
assert(len(docSentenceStructureList) == len(docTextProcessedSplit)), "Assertion Failed, array lengths don't match. " + str(len(docSentenceStructureList)) + " " + str(len(docTextProcessedSplit))
#Strip the extension from the file to get the document name
docName = os.path.splitext(document)[0]
#Add the SentenceStructureList to the dictionary
docDictionary[docName] = docSentenceStructureList
#Close the document
doc.close()
#Return to original path
os.chdir(cwd)
#Return the dictionary
return docDictionary