def indexFile(self, filepath, isPrivate=True):
docId = None
try:
if not self.isIndexable(filepath):
return
state = docState(isPrivate)
fileSize = os.path.getsize(filepath)
lastModificationTime = os.path.getmtime(filepath)
lastIdxTime, lastIdxState = self.getLastIndexationTimeAndState(filepath)
if lastIdxState == state and lastIdxTime >= lastModificationTime:
for obs in self.observers:
obs.documentUntouched(filepath, state)
print "%s didn't change since last indexation" % (safe_encode(filepath),)
return
try:
title, text, _, _ = converter.extractWordsFromFile(filepath)
except converter.IndexationFailure, exc:
raise FileIndexationFailure(safe_encode(filepath),
"converter thus complained : %s" % exc)
docId = makeDocumentId(filepath)
mime_type = mimetypes.guess_type(filepath)[0]
doc = FutureDocument(filename=filepath,
title=title, text=text,
fileSize=fileSize,
lastModificationTime=lastModificationTime,
content_hash=docId, mime_type=mime_type,
state=state)
self.indexDocument(doc)
def start(self):
existingFiles = Set()
for filename in self.getFileIterator():
existingFiles.add(filename)
if not self.isIndexable(filename):
continue
lastModificationTime = os.path.getmtime(filename)
lastIndexationTime = self.getLastIndexationTime(filename)
if lastIndexationTime >= lastModificationTime:
if self.verbose:
print "%s didn't change since last indexation" % filename
else:
fileSize = os.path.getsize(filename)
try:
title, text, links, offset = converter.extractWordsFromFile(filename)
except converter.IndexationFailure, exc:
if self.verbose:
print exc
continue
docId = makeDocumentId(filename)
mime_type = mimetypes.guess_type(filename)[0]
self.indexDocument(filename, title, text, fileSize,
lastModificationTime,
docId, mime_type, Document.PUBLISHED_STATE)
def start(self):
existingFiles = Set()
for filename in self.getFileIterator():
existingFiles.add(filename)
if not self.isIndexable(filename):
continue
lastModificationTime = os.path.getmtime(filename)
lastIndexationTime = self.getLastIndexationTime(filename)
if lastIndexationTime >= lastModificationTime:
if self.verbose:
print "%s didn't change since last indexation" % filename
else:
fileSize = os.path.getsize(filename)
try:
title, text, links, offset = converter.extractWordsFromFile(
filename)
except converter.IndexationFailure, exc:
if self.verbose:
print exc
continue
docId = makeDocumentId(filename)
mime_type = mimetypes.guess_type(filename)[0]
self.indexDocument(filename, title, text, fileSize,
lastModificationTime, docId, mime_type,
Document.PUBLISHED_STATE)
def runIndexer(self, isPrivate=True):
existingFiles = Set()
if isPrivate:
state = Document.PRIVATE_STATE
else:
state = Document.PUBLISHED_STATE
for filename in self.getFileIterator(isPrivate):
existingFiles.add(filename)
if not self.isIndexable(filename):
continue
lastModificationTime = os.path.getmtime(filename)
lastIdxTime, lastIdxState = self.getLastIndexationTimeAndState(
filename)
if lastIdxState == state and lastIdxTime >= lastModificationTime:
if self.verbose:
print "%s didn't change since last indexation" % filename
continue
else:
fileSize = os.path.getsize(filename)
try:
title, text, links, offset = converter.extractWordsFromFile(
filename)
except converter.IndexationFailure, exc:
if self.verbose:
print exc
continue
docId = makeDocumentId(filename)
mime_type = mimetypes.guess_type(filename)[0]
self.indexDocument(
FutureDocument(filename=unicode(filename,
self.filesystemEncoding),
title=title,
text=text,
fileSize=fileSize,
lastModificationTime=lastModificationTime,
content_hash=docId,
mime_type=mime_type,
state=state))
def runIndexer(self, isPrivate=True):
existingFiles = Set()
if isPrivate:
state = Document.PRIVATE_STATE
else:
state = Document.PUBLISHED_STATE
for filename in self.getFileIterator(isPrivate):
existingFiles.add(filename)
if not self.isIndexable(filename):
continue
lastModificationTime = os.path.getmtime(filename)
lastIdxTime, lastIdxState = self.getLastIndexationTimeAndState(filename)
if lastIdxState == state and lastIdxTime >= lastModificationTime:
if self.verbose:
print "%s didn't change since last indexation" % filename
continue
else:
fileSize = os.path.getsize(filename)
try:
title, text, links, offset = converter.extractWordsFromFile(filename)
except converter.IndexationFailure, exc:
if self.verbose:
print exc
continue
docId = makeDocumentId(filename)
mime_type = mimetypes.guess_type(filename)[0]
self.indexDocument(FutureDocument(filename=unicode(filename,
self.filesystemEncoding),
title=title, text=text,
fileSize=fileSize,
lastModificationTime=lastModificationTime,
content_hash=docId, mime_type=mime_type,
state=state))
