Python StringUtils.isTextType方法代码示例

# 需要导入模块: from pyaid.string.StringUtils import StringUtils [as 别名]
# 或者: from pyaid.string.StringUtils.StringUtils import isTextType [as 别名]
    def save(self, path =None):
        """ Saves the CSV file data to the specified path """
        if path is None:
            path = self.path

        if self.removeIfSavedEmpty and not self.rows:
            self.remove()
            return

        index = 0
        names = self.fieldNames
        if self.autoIndexFieldName:
            names.insert(0, self.autoIndexFieldName)

        try:
            with open(path, 'wb') as f:
                writer = csv.DictWriter(f, fieldnames=names, dialect=csv.excel)
                writer.writeheader()
                for row in self.rows:
                    result = dict()

                    if self.autoIndexFieldName:
                        index += 1
                        result[self.autoIndexFieldName] = index

                    for key, spec in DictUtils.iter(self._fields):
                        value = row.get(key, spec.get('empty', ''))
                        name = spec.get('name', key)
                        if StringUtils.isTextType(value):
                            value = value.encode('latin-1')
                        result[name] = value
                    writer.writerow(result)
            return True
        except Exception:
            return False

# 需要导入模块: from pyaid.string.StringUtils import StringUtils [as 别名]
# 或者: from pyaid.string.StringUtils.StringUtils import isTextType [as 别名]
    def save(self):
        """save doc..."""
        if self.removeIfSavedEmpty and not self.rows:
            self.remove()
            return

        index = 0
        names = self.fieldNames
        if self.autoIndexFieldName:
            names.insert(0, self.autoIndexFieldName)

        fieldNames = []
        for name in names:
            if StringUtils.isTextType(name):
                name = name.encode('latin-1')
            fieldNames.append(name)

        try:
            if sys.version < '3':
                args = dict(mode='w')
            else:
                args = dict(mode='w', encoding='utf-8')
            with open(self.path, **args) as f:
                writer = csv.DictWriter(f, fieldnames=names, dialect=csv.excel)
                writer.writeheader()
                for row in self.rows:
                    result = dict()

                    if self.autoIndexFieldName:
                        index += 1
                        result[self.autoIndexFieldName] = index

                    for key, name in self._fields.items():
                        value = row.get(key, '')
                        if StringUtils.isBinaryType(value):
                            value = StringUtils.toText(value)
                        result[name] = value
                    writer.writerow(result)
            return True
        except Exception as err:
            raise
            return False

# 需要导入模块: from pyaid.string.StringUtils import StringUtils [as 别名]
# 或者: from pyaid.string.StringUtils.StringUtils import isTextType [as 别名]
    def read(self, session, analysisSession, path =None, compressed =False):
        """ Reads from the spreadsheet located at the absolute path argument and adds each row
            to the tracks in the database. """

        if path is not None:
            self._path = path
        if self._path is None:
            return False

        model = Tracks_Track.MASTER
        for existingTrack in session.query(model).all():
            self.remainingTracks[existingTrack.uid] = existingTrack.fingerprint

        try:
            data = pd.read_csv(self._path)
        except Exception as err:
            self._writeError({
                'message':'ERROR: Unable to read CSV file "%s"' % self._path,
                'error':err })
            return

        if data is None:
            self._writeError({
                'message':'ERROR: Failed to create CSV reader for file "%s"' % self._path })
            return

        for index, row in data.iterrows():
            # Skip any rows that don't start with the proper numeric index value, which
            # includes the header row (if it exists) with the column names
            try:
                index = int(row[0])
            except Exception:
                continue

            rowDict = dict()
            for column in Reflection.getReflectionList(TrackCsvColumnEnum):
                value = row[column.index]

                if value and StringUtils.isStringType(value) and not StringUtils.isTextType(value):
                    # Try to decode the value into a unicode string using common codecs
                    for codec in ['utf8', 'MacRoman', 'utf16']:
                        try:
                            decodedValue = value.decode(codec)
                            if decodedValue:
                                value = decodedValue
                                break
                        except Exception:
                            continue

                try:
                    # Check to see if the value is NaN, and if it is replace it with an empty
                    # string to be ignored during import
                    value = '' if np.isnan(value) else value
                except Exception:
                    pass

                if value != '' or value is None:
                    rowDict[column.name] = value

            self.fromSpreadsheetEntry(rowDict, session)

        for uid, fingerprint in DictUtils.iter(self.remainingTracks):
            # Iterate through the list of remaining tracks, which are tracks not found by the
            # importer. If the track is marked as custom (meaning it is not managed by the importer)
            # it is ignored. Otherwise, the track is deleted from the database as a track that no
            # longer exists.

            track = Tracks_Track.MASTER.getByUid(uid, session)
            if track.custom:
                continue

            Tracks_Track.removeTrack(track, analysisSession)
            self._logger.write('[REMOVED]: No longer exists "%s" (%s)' % (
                track.fingerprint, track.uid))

        session.flush()

        for track in self.created:
            self._logger.write('[CREATED]: "%s" (%s)' % (track.fingerprint, track.uid))

        return True