GitHub/Anki
1
0
Fork 0
mirror of https://github.com/ankitects/anki.git synced 2025-09-19 22:42:25 -04:00
Code Issues Projects Releases Packages 1 Wiki Activity Actions

initMapping(); csv tweaks

Browse source
This commit is contained in:
Damien Elmes 2012-02-29 13:33:55 +09:00
parent 44dea8211e
commit a99101d95c
3 changed files with 18 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
anki/importing/csvfile.py
View file

@ -20,7 +20,7 @@ class TextImporter(NoteImporter):
self.tagsToAdd = [] self.tagsToAdd = []
def foreignNotes(self): def foreignNotes(self):
self.sniff() self.open()
# process all lines # process all lines
log = [] log = []
notes = [] notes = []
@ -31,12 +31,7 @@ class TextImporter(NoteImporter):
else: else:
reader = csv.reader(self.data, self.dialect, doublequote=True) reader = csv.reader(self.data, self.dialect, doublequote=True)
for row in reader: for row in reader:
try: row = [unicode(x, "utf-8") for x in row]
row = [unicode(x, "utf-8") for x in row]
except UnicodeDecodeError, e:
raise ImportFormatError(
type="encodingError",
info=_("Please save in UTF-8 format. Click help for info."))
if len(row) != self.numFields: if len(row) != self.numFields:
log.append(_( log.append(_(
"'%(row)s' had %(num1)d fields, " "'%(row)s' had %(num1)d fields, "
@ -54,7 +49,7 @@ class TextImporter(NoteImporter):
self.fileobj.close() self.fileobj.close()
return notes return notes
def sniff(self): def open(self):
"Parse the top line and determine the pattern and number of fields." "Parse the top line and determine the pattern and number of fields."
# load & look for the right pattern # load & look for the right pattern
self.cacheFile() self.cacheFile()
@ -79,15 +74,11 @@ class TextImporter(NoteImporter):
del self.data[0] del self.data[0]
self.updateDelimiter() self.updateDelimiter()
if not self.dialect and not self.delimiter: if not self.dialect and not self.delimiter:
raise ImportFormatError( raise Exception("unknownFormat")
type="encodingError",
info=_("Couldn't determine format of file."))
def updateDelimiter(self): def updateDelimiter(self):
def err(): def err():
raise ImportFormatError( raise Exception("unknownFormat")
type="encodingError",
info=_("File is not encoded in UTF-8."))
self.dialect = None self.dialect = None
sniffer = csv.Sniffer() sniffer = csv.Sniffer()
delims = [',', '\t', ';', ':'] delims = [',', '\t', ';', ':']
@ -123,7 +114,7 @@ class TextImporter(NoteImporter):
def fields(self): def fields(self):
"Number of fields." "Number of fields."
self.sniff() self.open()
return self.numFields return self.numFields
def noteFromFields(self, fields): def noteFromFields(self, fields):

15
anki/importing/noteimp.py
View file

@ -51,15 +51,22 @@ class NoteImporter(Importer):
"The number of fields." "The number of fields."
return 0 return 0
def maybeChecksum(self, data, unique): def initMapping(self):
if not unique: flds = [f['name'] for f in self.model['flds']]
return "" # truncate to provided count
return fieldChecksum(data) flds = flds[0:self.fields()]
# if provided count is greater, pad
flds = flds + [None] * (self.fields() - len(flds))
self.mapping = flds
def foreignNotes(self): def foreignNotes(self):
"Return a list of foreign notes for importing." "Return a list of foreign notes for importing."
assert 0 assert 0
def open(self):
"Open file and ensure it's in the right format."
assert 0
def importNotes(self, notes): def importNotes(self, notes):
"Convert each card into a note, apply attributes and add to col." "Convert each card into a note, apply attributes and add to col."
# gather checks for duplicate comparison # gather checks for duplicate comparison

2
tests/test_importing.py
View file

@ -80,7 +80,7 @@ def test_csv():
deck = getEmptyDeck() deck = getEmptyDeck()
file = unicode(os.path.join(testDir, "support/text-2fields.txt")) file = unicode(os.path.join(testDir, "support/text-2fields.txt"))
i = TextImporter(deck, file) i = TextImporter(deck, file)
i.mapping = ['Front', 'Back'] i.initMapping()
i.run() i.run()
# four problems - too many & too few fields, a missing front, and a # four problems - too many & too few fields, a missing front, and a
# duplicate entry # duplicate entry