Projects/worblehat-old
Archived
12
0
Fork 0
Code Issues Pull Requests Activity

faset over fra Z3950 til google books

Browse Source
This commit is contained in:
Øyvind Almelid
2010-09-23 13:57:37 +00:00
parent d173b9396e
commit 644e79f9b5
221 changed files with 60948 additions and 27273 deletions
Download Patch File Download Diff File Expand all files Collapse all files

474
python/gdata/spreadsheet/__init__.py Normal file
View File

@@ -0,0 +1,474 @@
#!/usr/bin/python
#
# Copyright (C) 2007 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Contains extensions to Atom objects used with Google Spreadsheets.
"""
__author__ = 'api.laurabeth@gmail.com (Laura Beth Lincoln)'
try:
from xml.etree import cElementTree as ElementTree
except ImportError:
try:
import cElementTree as ElementTree
except ImportError:
try:
from xml.etree import ElementTree
except ImportError:
from elementtree import ElementTree
import atom
import gdata
import re
import string
# XML namespaces which are often used in Google Spreadsheets entities.
GSPREADSHEETS_NAMESPACE = 'http://schemas.google.com/spreadsheets/2006'
GSPREADSHEETS_TEMPLATE = '{http://schemas.google.com/spreadsheets/2006}%s'
GSPREADSHEETS_EXTENDED_NAMESPACE = ('http://schemas.google.com/spreadsheets'
'/2006/extended')
GSPREADSHEETS_EXTENDED_TEMPLATE = ('{http://schemas.google.com/spreadsheets'
'/2006/extended}%s')
class ColCount(atom.AtomBase):
"""The Google Spreadsheets colCount element """
_tag = 'colCount'
_namespace = GSPREADSHEETS_NAMESPACE
_children = atom.AtomBase._children.copy()
_attributes = atom.AtomBase._attributes.copy()
def __init__(self, text=None, extension_elements=None,
extension_attributes=None):
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def ColCountFromString(xml_string):
return atom.CreateClassFromXMLString(ColCount, xml_string)
class RowCount(atom.AtomBase):
"""The Google Spreadsheets rowCount element """
_tag = 'rowCount'
_namespace = GSPREADSHEETS_NAMESPACE
_children = atom.AtomBase._children.copy()
_attributes = atom.AtomBase._attributes.copy()
def __init__(self, text=None, extension_elements=None,
extension_attributes=None):
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def RowCountFromString(xml_string):
return atom.CreateClassFromXMLString(RowCount, xml_string)
class Cell(atom.AtomBase):
"""The Google Spreadsheets cell element """
_tag = 'cell'
_namespace = GSPREADSHEETS_NAMESPACE
_children = atom.AtomBase._children.copy()
_attributes = atom.AtomBase._attributes.copy()
_attributes['row'] = 'row'
_attributes['col'] = 'col'
_attributes['inputValue'] = 'inputValue'
_attributes['numericValue'] = 'numericValue'
def __init__(self, text=None, row=None, col=None, inputValue=None,
numericValue=None, extension_elements=None, extension_attributes=None):
self.text = text
self.row = row
self.col = col
self.inputValue = inputValue
self.numericValue = numericValue
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def CellFromString(xml_string):
return atom.CreateClassFromXMLString(Cell, xml_string)
class Custom(atom.AtomBase):
"""The Google Spreadsheets custom element"""
_namespace = GSPREADSHEETS_EXTENDED_NAMESPACE
_children = atom.AtomBase._children.copy()
_attributes = atom.AtomBase._attributes.copy()
def __init__(self, column=None, text=None, extension_elements=None,
extension_attributes=None):
self.column = column # The name of the column
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def _BecomeChildElement(self, tree):
new_child = ElementTree.Element('')
tree.append(new_child)
new_child.tag = '{%s}%s' % (self.__class__._namespace,
self.column)
self._AddMembersToElementTree(new_child)
def _ToElementTree(self):
new_tree = ElementTree.Element('{%s}%s' % (self.__class__._namespace,
self.column))
self._AddMembersToElementTree(new_tree)
return new_tree
def _HarvestElementTree(self, tree):
namespace_uri, local_tag = string.split(tree.tag[1:], "}", 1)
self.column = local_tag
# Fill in the instance members from the contents of the XML tree.
for child in tree:
self._ConvertElementTreeToMember(child)
for attribute, value in tree.attrib.iteritems():
self._ConvertElementAttributeToMember(attribute, value)
self.text = tree.text
def CustomFromString(xml_string):
element_tree = ElementTree.fromstring(xml_string)
return _CustomFromElementTree(element_tree)
def _CustomFromElementTree(element_tree):
namespace_uri, local_tag = string.split(element_tree.tag[1:], "}", 1)
if namespace_uri == GSPREADSHEETS_EXTENDED_NAMESPACE:
new_custom = Custom()
new_custom._HarvestElementTree(element_tree)
new_custom.column = local_tag
return new_custom
return None
class SpreadsheetsSpreadsheet(gdata.GDataEntry):
"""A Google Spreadsheets flavor of a Spreadsheet Atom Entry """
_tag = 'entry'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataEntry._children.copy()
_attributes = gdata.GDataEntry._attributes.copy()
def __init__(self, author=None, category=None, content=None,
contributor=None, atom_id=None, link=None, published=None, rights=None,
source=None, summary=None, title=None, control=None, updated=None,
text=None, extension_elements=None, extension_attributes=None):
self.author = author or []
self.category = category or []
self.content = content
self.contributor = contributor or []
self.id = atom_id
self.link = link or []
self.published = published
self.rights = rights
self.source = source
self.summary = summary
self.control = control
self.title = title
self.updated = updated
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def SpreadsheetsSpreadsheetFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsSpreadsheet,
xml_string)
class SpreadsheetsWorksheet(gdata.GDataEntry):
"""A Google Spreadsheets flavor of a Worksheet Atom Entry """
_tag = 'entry'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataEntry._children.copy()
_attributes = gdata.GDataEntry._attributes.copy()
_children['{%s}rowCount' % GSPREADSHEETS_NAMESPACE] = ('row_count',
RowCount)
_children['{%s}colCount' % GSPREADSHEETS_NAMESPACE] = ('col_count',
ColCount)
def __init__(self, author=None, category=None, content=None,
contributor=None, atom_id=None, link=None, published=None, rights=None,
source=None, summary=None, title=None, control=None, updated=None,
row_count=None, col_count=None, text=None, extension_elements=None,
extension_attributes=None):
self.author = author or []
self.category = category or []
self.content = content
self.contributor = contributor or []
self.id = atom_id
self.link = link or []
self.published = published
self.rights = rights
self.source = source
self.summary = summary
self.control = control
self.title = title
self.updated = updated
self.row_count = row_count
self.col_count = col_count
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def SpreadsheetsWorksheetFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsWorksheet,
xml_string)
class SpreadsheetsCell(gdata.BatchEntry):
"""A Google Spreadsheets flavor of a Cell Atom Entry """
_tag = 'entry'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.BatchEntry._children.copy()
_attributes = gdata.BatchEntry._attributes.copy()
_children['{%s}cell' % GSPREADSHEETS_NAMESPACE] = ('cell', Cell)
def __init__(self, author=None, category=None, content=None,
contributor=None, atom_id=None, link=None, published=None, rights=None,
source=None, summary=None, title=None, control=None, updated=None,
cell=None, batch_operation=None, batch_id=None, batch_status=None,
text=None, extension_elements=None, extension_attributes=None):
self.author = author or []
self.category = category or []
self.content = content
self.contributor = contributor or []
self.id = atom_id
self.link = link or []
self.published = published
self.rights = rights
self.source = source
self.summary = summary
self.control = control
self.title = title
self.batch_operation = batch_operation
self.batch_id = batch_id
self.batch_status = batch_status
self.updated = updated
self.cell = cell
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
def SpreadsheetsCellFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsCell,
xml_string)
class SpreadsheetsList(gdata.GDataEntry):
"""A Google Spreadsheets flavor of a List Atom Entry """
_tag = 'entry'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataEntry._children.copy()
_attributes = gdata.GDataEntry._attributes.copy()
def __init__(self, author=None, category=None, content=None,
contributor=None, atom_id=None, link=None, published=None, rights=None,
source=None, summary=None, title=None, control=None, updated=None,
custom=None,
text=None, extension_elements=None, extension_attributes=None):
self.author = author or []
self.category = category or []
self.content = content
self.contributor = contributor or []
self.id = atom_id
self.link = link or []
self.published = published
self.rights = rights
self.source = source
self.summary = summary
self.control = control
self.title = title
self.updated = updated
self.custom = custom or {}
self.text = text
self.extension_elements = extension_elements or []
self.extension_attributes = extension_attributes or {}
# We need to overwrite _ConvertElementTreeToMember to add special logic to
# convert custom attributes to members
def _ConvertElementTreeToMember(self, child_tree):
# Find the element's tag in this class's list of child members
if self.__class__._children.has_key(child_tree.tag):
member_name = self.__class__._children[child_tree.tag][0]
member_class = self.__class__._children[child_tree.tag][1]
# If the class member is supposed to contain a list, make sure the
# matching member is set to a list, then append the new member
# instance to the list.
if isinstance(member_class, list):
if getattr(self, member_name) is None:
setattr(self, member_name, [])
getattr(self, member_name).append(atom._CreateClassFromElementTree(
member_class[0], child_tree))
else:
setattr(self, member_name,
atom._CreateClassFromElementTree(member_class, child_tree))
elif child_tree.tag.find('{%s}' % GSPREADSHEETS_EXTENDED_NAMESPACE) == 0:
# If this is in the custom namespace, make add it to the custom dict.
name = child_tree.tag[child_tree.tag.index('}')+1:]
custom = _CustomFromElementTree(child_tree)
if custom:
self.custom[name] = custom
else:
atom.ExtensionContainer._ConvertElementTreeToMember(self, child_tree)
# We need to overwtite _AddMembersToElementTree to add special logic to
# convert custom members to XML nodes.
def _AddMembersToElementTree(self, tree):
# Convert the members of this class which are XML child nodes.
# This uses the class's _children dictionary to find the members which
# should become XML child nodes.
member_node_names = [values[0] for tag, values in
self.__class__._children.iteritems()]
for member_name in member_node_names:
member = getattr(self, member_name)
if member is None:
pass
elif isinstance(member, list):
for instance in member:
instance._BecomeChildElement(tree)
else:
member._BecomeChildElement(tree)
# Convert the members of this class which are XML attributes.
for xml_attribute, member_name in self.__class__._attributes.iteritems():
member = getattr(self, member_name)
if member is not None:
tree.attrib[xml_attribute] = member
# Convert all special custom item attributes to nodes
for name, custom in self.custom.iteritems():
custom._BecomeChildElement(tree)
# Lastly, call the ExtensionContainers's _AddMembersToElementTree to
# convert any extension attributes.
atom.ExtensionContainer._AddMembersToElementTree(self, tree)
def SpreadsheetsListFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsList,
xml_string)
element_tree = ElementTree.fromstring(xml_string)
return _SpreadsheetsListFromElementTree(element_tree)
class SpreadsheetsSpreadsheetsFeed(gdata.GDataFeed):
"""A feed containing Google Spreadsheets Spreadsheets"""
_tag = 'feed'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataFeed._children.copy()
_attributes = gdata.GDataFeed._attributes.copy()
_children['{%s}entry' % atom.ATOM_NAMESPACE] = ('entry',
[SpreadsheetsSpreadsheet])
def SpreadsheetsSpreadsheetsFeedFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsSpreadsheetsFeed,
xml_string)
class SpreadsheetsWorksheetsFeed(gdata.GDataFeed):
"""A feed containing Google Spreadsheets Spreadsheets"""
_tag = 'feed'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataFeed._children.copy()
_attributes = gdata.GDataFeed._attributes.copy()
_children['{%s}entry' % atom.ATOM_NAMESPACE] = ('entry',
[SpreadsheetsWorksheet])
def SpreadsheetsWorksheetsFeedFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsWorksheetsFeed,
xml_string)
class SpreadsheetsCellsFeed(gdata.BatchFeed):
"""A feed containing Google Spreadsheets Cells"""
_tag = 'feed'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.BatchFeed._children.copy()
_attributes = gdata.BatchFeed._attributes.copy()
_children['{%s}entry' % atom.ATOM_NAMESPACE] = ('entry',
[SpreadsheetsCell])
_children['{%s}rowCount' % GSPREADSHEETS_NAMESPACE] = ('row_count',
RowCount)
_children['{%s}colCount' % GSPREADSHEETS_NAMESPACE] = ('col_count',
ColCount)
def __init__(self, author=None, category=None, contributor=None,
generator=None, icon=None, atom_id=None, link=None, logo=None,
rights=None, subtitle=None, title=None, updated=None,
entry=None, total_results=None, start_index=None,
items_per_page=None, extension_elements=None,
extension_attributes=None, text=None, row_count=None,
col_count=None, interrupted=None):
gdata.BatchFeed.__init__(self, author=author, category=category,
contributor=contributor, generator=generator,
icon=icon, atom_id=atom_id, link=link,
logo=logo, rights=rights, subtitle=subtitle,
title=title, updated=updated, entry=entry,
total_results=total_results,
start_index=start_index,
items_per_page=items_per_page,
extension_elements=extension_elements,
extension_attributes=extension_attributes,
text=text, interrupted=interrupted)
self.row_count = row_count
self.col_count = col_count
def GetBatchLink(self):
for link in self.link:
if link.rel == 'http://schemas.google.com/g/2005#batch':
return link
return None
def SpreadsheetsCellsFeedFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsCellsFeed,
xml_string)
class SpreadsheetsListFeed(gdata.GDataFeed):
"""A feed containing Google Spreadsheets Spreadsheets"""
_tag = 'feed'
_namespace = atom.ATOM_NAMESPACE
_children = gdata.GDataFeed._children.copy()
_attributes = gdata.GDataFeed._attributes.copy()
_children['{%s}entry' % atom.ATOM_NAMESPACE] = ('entry',
[SpreadsheetsList])
def SpreadsheetsListFeedFromString(xml_string):
return atom.CreateClassFromXMLString(SpreadsheetsListFeed,
xml_string)

484
python/gdata/spreadsheet/service.py Normal file
View File

@@ -0,0 +1,484 @@
#!/usr/bin/python
#
# Copyright (C) 2007 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""SpreadsheetsService extends the GDataService to streamline Google
Spreadsheets operations.
SpreadsheetService: Provides methods to query feeds and manipulate items.
Extends GDataService.
DictionaryToParamList: Function which converts a dictionary into a list of
URL arguments (represented as strings). This is a
utility function used in CRUD operations.
"""
__author__ = 'api.laurabeth@gmail.com (Laura Beth Lincoln)'
import gdata
import atom.service
import gdata.service
import gdata.spreadsheet
import atom
class Error(Exception):
"""Base class for exceptions in this module."""
pass
class RequestError(Error):
pass
class SpreadsheetsService(gdata.service.GDataService):
"""Client for the Google Spreadsheets service."""
def __init__(self, email=None, password=None, source=None,
server='spreadsheets.google.com', additional_headers=None,
**kwargs):
"""Creates a client for the Google Spreadsheets service.
Args:
email: string (optional) The user's email address, used for
authentication.
password: string (optional) The user's password.
source: string (optional) The name of the user's application.
server: string (optional) The name of the server to which a connection
will be opened. Default value: 'spreadsheets.google.com'.
**kwargs: The other parameters to pass to gdata.service.GDataService
constructor.
"""
gdata.service.GDataService.__init__(
self, email=email, password=password, service='wise', source=source,
server=server, additional_headers=additional_headers, **kwargs)
def GetSpreadsheetsFeed(self, key=None, query=None, visibility='private',
projection='full'):
"""Gets a spreadsheets feed or a specific entry if a key is defined
Args:
key: string (optional) The spreadsheet key defined in /ccc?key=
query: DocumentQuery (optional) Query parameters
Returns:
If there is no key, then a SpreadsheetsSpreadsheetsFeed.
If there is a key, then a SpreadsheetsSpreadsheet.
"""
uri = ('https://%s/feeds/spreadsheets/%s/%s'
% (self.server, visibility, projection))
if key is not None:
uri = '%s/%s' % (uri, key)
if query != None:
query.feed = uri
uri = query.ToUri()
if key:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsSpreadsheetFromString)
else:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsSpreadsheetsFeedFromString)
def GetWorksheetsFeed(self, key, wksht_id=None, query=None,
visibility='private', projection='full'):
"""Gets a worksheets feed or a specific entry if a wksht is defined
Args:
key: string The spreadsheet key defined in /ccc?key=
wksht_id: string (optional) The id for a specific worksheet entry
query: DocumentQuery (optional) Query parameters
Returns:
If there is no wksht_id, then a SpreadsheetsWorksheetsFeed.
If there is a wksht_id, then a SpreadsheetsWorksheet.
"""
uri = ('https://%s/feeds/worksheets/%s/%s/%s'
% (self.server, key, visibility, projection))
if wksht_id != None:
uri = '%s/%s' % (uri, wksht_id)
if query != None:
query.feed = uri
uri = query.ToUri()
if wksht_id:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsWorksheetFromString)
else:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsWorksheetsFeedFromString)
def AddWorksheet(self, title, row_count, col_count, key):
"""Creates a new worksheet in the desired spreadsheet.
The new worksheet is appended to the end of the list of worksheets. The
new worksheet will only have the available number of columns and cells
specified.
Args:
title: str The title which will be displayed in the list of worksheets.
row_count: int or str The number of rows in the new worksheet.
col_count: int or str The number of columns in the new worksheet.
key: str The spreadsheet key to the spreadsheet to which the new
worksheet should be added.
Returns:
A SpreadsheetsWorksheet if the new worksheet was created succesfully.
"""
new_worksheet = gdata.spreadsheet.SpreadsheetsWorksheet(
title=atom.Title(text=title),
row_count=gdata.spreadsheet.RowCount(text=str(row_count)),
col_count=gdata.spreadsheet.ColCount(text=str(col_count)))
return self.Post(new_worksheet,
'https://%s/feeds/worksheets/%s/private/full' % (self.server, key),
converter=gdata.spreadsheet.SpreadsheetsWorksheetFromString)
def UpdateWorksheet(self, worksheet_entry, url=None):
"""Changes the size and/or title of the desired worksheet.
Args:
worksheet_entry: SpreadsheetWorksheet The new contents of the
worksheet.
url: str (optional) The URL to which the edited worksheet entry should
be sent. If the url is None, the edit URL from the worksheet will
be used.
Returns:
A SpreadsheetsWorksheet with the new information about the worksheet.
"""
target_url = url or worksheet_entry.GetEditLink().href
return self.Put(worksheet_entry, target_url,
converter=gdata.spreadsheet.SpreadsheetsWorksheetFromString)
def DeleteWorksheet(self, worksheet_entry=None, url=None):
"""Removes the desired worksheet from the spreadsheet
Args:
worksheet_entry: SpreadsheetWorksheet (optional) The worksheet to
be deleted. If this is none, then the DELETE reqest is sent to
the url specified in the url parameter.
url: str (optaional) The URL to which the DELETE request should be
sent. If left as None, the worksheet's edit URL is used.
Returns:
True if the worksheet was deleted successfully.
"""
if url:
target_url = url
else:
target_url = worksheet_entry.GetEditLink().href
return self.Delete(target_url)
def GetCellsFeed(self, key, wksht_id='default', cell=None, query=None,
visibility='private', projection='full'):
"""Gets a cells feed or a specific entry if a cell is defined
Args:
key: string The spreadsheet key defined in /ccc?key=
wksht_id: string The id for a specific worksheet entry
cell: string (optional) The R1C1 address of the cell
query: DocumentQuery (optional) Query parameters
Returns:
If there is no cell, then a SpreadsheetsCellsFeed.
If there is a cell, then a SpreadsheetsCell.
"""
uri = ('https://%s/feeds/cells/%s/%s/%s/%s'
% (self.server, key, wksht_id, visibility, projection))
if cell != None:
uri = '%s/%s' % (uri, cell)
if query != None:
query.feed = uri
uri = query.ToUri()
if cell:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsCellFromString)
else:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsCellsFeedFromString)
def GetListFeed(self, key, wksht_id='default', row_id=None, query=None,
visibility='private', projection='full'):
"""Gets a list feed or a specific entry if a row_id is defined
Args:
key: string The spreadsheet key defined in /ccc?key=
wksht_id: string The id for a specific worksheet entry
row_id: string (optional) The row_id of a row in the list
query: DocumentQuery (optional) Query parameters
Returns:
If there is no row_id, then a SpreadsheetsListFeed.
If there is a row_id, then a SpreadsheetsList.
"""
uri = ('https://%s/feeds/list/%s/%s/%s/%s'
% (self.server, key, wksht_id, visibility, projection))
if row_id is not None:
uri = '%s/%s' % (uri, row_id)
if query is not None:
query.feed = uri
uri = query.ToUri()
if row_id:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsListFromString)
else:
return self.Get(uri,
converter=gdata.spreadsheet.SpreadsheetsListFeedFromString)
def UpdateCell(self, row, col, inputValue, key, wksht_id='default'):
"""Updates an existing cell.
Args:
row: int The row the cell to be editted is in
col: int The column the cell to be editted is in
inputValue: str the new value of the cell
key: str The key of the spreadsheet in which this cell resides.
wksht_id: str The ID of the worksheet which holds this cell.
Returns:
The updated cell entry
"""
row = str(row)
col = str(col)
# make the new cell
new_cell = gdata.spreadsheet.Cell(row=row, col=col, inputValue=inputValue)
# get the edit uri and PUT
cell = 'R%sC%s' % (row, col)
entry = self.GetCellsFeed(key, wksht_id, cell)
for a_link in entry.link:
if a_link.rel == 'edit':
entry.cell = new_cell
return self.Put(entry, a_link.href,
converter=gdata.spreadsheet.SpreadsheetsCellFromString)
def _GenerateCellsBatchUrl(self, spreadsheet_key, worksheet_id):
return ('https://spreadsheets.google.com/feeds/cells/%s/%s/'
'private/full/batch' % (spreadsheet_key, worksheet_id))
def ExecuteBatch(self, batch_feed, url=None, spreadsheet_key=None,
worksheet_id=None,
converter=gdata.spreadsheet.SpreadsheetsCellsFeedFromString):
"""Sends a batch request feed to the server.
The batch request needs to be sent to the batch URL for a particular
worksheet. You can specify the worksheet by providing the spreadsheet_key
and worksheet_id, or by sending the URL from the cells feed's batch link.
Args:
batch_feed: gdata.spreadsheet.SpreadsheetsCellFeed A feed containing
BatchEntry elements which contain the desired CRUD operation and
any necessary data to modify a cell.
url: str (optional) The batch URL for the cells feed to which these
changes should be applied. This can be found by calling
cells_feed.GetBatchLink().href.
spreadsheet_key: str (optional) Used to generate the batch request URL
if the url argument is None. If using the spreadsheet key to
generate the URL, the worksheet id is also required.
worksheet_id: str (optional) Used if the url is not provided, it is
oart of the batch feed target URL. This is used with the spreadsheet
key.
converter: Function (optional) Function to be executed on the server's
response. This function should take one string as a parameter. The
default value is SpreadsheetsCellsFeedFromString which will turn the result
into a gdata.spreadsheet.SpreadsheetsCellsFeed object.
Returns:
A gdata.BatchFeed containing the results.
"""
if url is None:
url = self._GenerateCellsBatchUrl(spreadsheet_key, worksheet_id)
return self.Post(batch_feed, url, converter=converter)
def InsertRow(self, row_data, key, wksht_id='default'):
"""Inserts a new row with the provided data
Args:
uri: string The post uri of the list feed
row_data: dict A dictionary of column header to row data
Returns:
The inserted row
"""
new_entry = gdata.spreadsheet.SpreadsheetsList()
for k, v in row_data.iteritems():
new_custom = gdata.spreadsheet.Custom()
new_custom.column = k
new_custom.text = v
new_entry.custom[new_custom.column] = new_custom
# Generate the post URL for the worksheet which will receive the new entry.
post_url = 'https://spreadsheets.google.com/feeds/list/%s/%s/private/full'%(
key, wksht_id)
return self.Post(new_entry, post_url,
converter=gdata.spreadsheet.SpreadsheetsListFromString)
def UpdateRow(self, entry, new_row_data):
"""Updates a row with the provided data
If you want to add additional information to a row, it is often
easier to change the values in entry.custom, then use the Put
method instead of UpdateRow. This UpdateRow method will replace
the contents of the row with new_row_data - it will change all columns
not just the columns specified in the new_row_data dict.
Args:
entry: gdata.spreadsheet.SpreadsheetsList The entry to be updated
new_row_data: dict A dictionary of column header to row data
Returns:
The updated row
"""
entry.custom = {}
for k, v in new_row_data.iteritems():
new_custom = gdata.spreadsheet.Custom()
new_custom.column = k
new_custom.text = v
entry.custom[k] = new_custom
for a_link in entry.link:
if a_link.rel == 'edit':
return self.Put(entry, a_link.href,
converter=gdata.spreadsheet.SpreadsheetsListFromString)
def DeleteRow(self, entry):
"""Deletes a row, the provided entry
Args:
entry: gdata.spreadsheet.SpreadsheetsList The row to be deleted
Returns:
The delete response
"""
for a_link in entry.link:
if a_link.rel == 'edit':
return self.Delete(a_link.href)
class DocumentQuery(gdata.service.Query):
def _GetTitleQuery(self):
return self['title']
def _SetTitleQuery(self, document_query):
self['title'] = document_query
title = property(_GetTitleQuery, _SetTitleQuery,
doc="""The title query parameter""")
def _GetTitleExactQuery(self):
return self['title-exact']
def _SetTitleExactQuery(self, document_query):
self['title-exact'] = document_query
title_exact = property(_GetTitleExactQuery, _SetTitleExactQuery,
doc="""The title-exact query parameter""")
class CellQuery(gdata.service.Query):
def _GetMinRowQuery(self):
return self['min-row']
def _SetMinRowQuery(self, cell_query):
self['min-row'] = cell_query
min_row = property(_GetMinRowQuery, _SetMinRowQuery,
doc="""The min-row query parameter""")
def _GetMaxRowQuery(self):
return self['max-row']
def _SetMaxRowQuery(self, cell_query):
self['max-row'] = cell_query
max_row = property(_GetMaxRowQuery, _SetMaxRowQuery,
doc="""The max-row query parameter""")
def _GetMinColQuery(self):
return self['min-col']
def _SetMinColQuery(self, cell_query):
self['min-col'] = cell_query
min_col = property(_GetMinColQuery, _SetMinColQuery,
doc="""The min-col query parameter""")
def _GetMaxColQuery(self):
return self['max-col']
def _SetMaxColQuery(self, cell_query):
self['max-col'] = cell_query
max_col = property(_GetMaxColQuery, _SetMaxColQuery,
doc="""The max-col query parameter""")
def _GetRangeQuery(self):
return self['range']
def _SetRangeQuery(self, cell_query):
self['range'] = cell_query
range = property(_GetRangeQuery, _SetRangeQuery,
doc="""The range query parameter""")
def _GetReturnEmptyQuery(self):
return self['return-empty']
def _SetReturnEmptyQuery(self, cell_query):
self['return-empty'] = cell_query
return_empty = property(_GetReturnEmptyQuery, _SetReturnEmptyQuery,
doc="""The return-empty query parameter""")
class ListQuery(gdata.service.Query):
def _GetSpreadsheetQuery(self):
return self['sq']
def _SetSpreadsheetQuery(self, list_query):
self['sq'] = list_query
sq = property(_GetSpreadsheetQuery, _SetSpreadsheetQuery,
doc="""The sq query parameter""")
def _GetOrderByQuery(self):
return self['orderby']
def _SetOrderByQuery(self, list_query):
self['orderby'] = list_query
orderby = property(_GetOrderByQuery, _SetOrderByQuery,
doc="""The orderby query parameter""")
def _GetReverseQuery(self):
return self['reverse']
def _SetReverseQuery(self, list_query):
self['reverse'] = list_query
reverse = property(_GetReverseQuery, _SetReverseQuery,
doc="""The reverse query parameter""")

559
python/gdata/spreadsheet/text_db.py Normal file
View File

@@ -0,0 +1,559 @@
#!/usr/bin/python
#
# Copyright Google 2007-2008, all rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import StringIO
import gdata
import gdata.service
import gdata.spreadsheet
import gdata.spreadsheet.service
import gdata.docs
import gdata.docs.service
"""Make the Google Documents API feel more like using a database.
This module contains a client and other classes which make working with the
Google Documents List Data API and the Google Spreadsheets Data API look a
bit more like working with a heirarchical database. Using the DatabaseClient,
you can create or find spreadsheets and use them like a database, with
worksheets representing tables and rows representing records.
Example Usage:
# Create a new database, a new table, and add records.
client = gdata.spreadsheet.text_db.DatabaseClient(username='jo@example.com',
password='12345')
database = client.CreateDatabase('My Text Database')
table = database.CreateTable('addresses', ['name','email',
'phonenumber', 'mailingaddress'])
record = table.AddRecord({'name':'Bob', 'email':'bob@example.com',
'phonenumber':'555-555-1234', 'mailingaddress':'900 Imaginary St.'})
# Edit a record
record.content['email'] = 'bob2@example.com'
record.Push()
# Delete a table
table.Delete
Warnings:
Care should be exercised when using this module on spreadsheets
which contain formulas. This module treats all rows as containing text and
updating a row will overwrite any formula with the output of the formula.
The intended use case is to allow easy storage of text data in a spreadsheet.
Error: Domain specific extension of Exception.
BadCredentials: Error raised is username or password was incorrect.
CaptchaRequired: Raised if a login attempt failed and a CAPTCHA challenge
was issued.
DatabaseClient: Communicates with Google Docs APIs servers.
Database: Represents a spreadsheet and interacts with tables.
Table: Represents a worksheet and interacts with records.
RecordResultSet: A list of records in a table.
Record: Represents a row in a worksheet allows manipulation of text data.
"""
__author__ = 'api.jscudder (Jeffrey Scudder)'
class Error(Exception):
pass
class BadCredentials(Error):
pass
class CaptchaRequired(Error):
pass
class DatabaseClient(object):
"""Allows creation and finding of Google Spreadsheets databases.
The DatabaseClient simplifies the process of creating and finding Google
Spreadsheets and will talk to both the Google Spreadsheets API and the
Google Documents List API.
"""
def __init__(self, username=None, password=None):
"""Constructor for a Database Client.
If the username and password are present, the constructor will contact
the Google servers to authenticate.
Args:
username: str (optional) Example: jo@example.com
password: str (optional)
"""
self.__docs_client = gdata.docs.service.DocsService()
self.__spreadsheets_client = (
gdata.spreadsheet.service.SpreadsheetsService())
self.SetCredentials(username, password)
def SetCredentials(self, username, password):
"""Attempts to log in to Google APIs using the provided credentials.
If the username or password are None, the client will not request auth
tokens.
Args:
username: str (optional) Example: jo@example.com
password: str (optional)
"""
self.__docs_client.email = username
self.__docs_client.password = password
self.__spreadsheets_client.email = username
self.__spreadsheets_client.password = password
if username and password:
try:
self.__docs_client.ProgrammaticLogin()
self.__spreadsheets_client.ProgrammaticLogin()
except gdata.service.CaptchaRequired:
raise CaptchaRequired('Please visit https://www.google.com/accounts/'
'DisplayUnlockCaptcha to unlock your account.')
except gdata.service.BadAuthentication:
raise BadCredentials('Username or password incorrect.')
def CreateDatabase(self, name):
"""Creates a new Google Spreadsheet with the desired name.
Args:
name: str The title for the spreadsheet.
Returns:
A Database instance representing the new spreadsheet.
"""
# Create a Google Spreadsheet to form the foundation of this database.
# Spreadsheet is created by uploading a file to the Google Documents
# List API.
virtual_csv_file = StringIO.StringIO(',,,')
virtual_media_source = gdata.MediaSource(file_handle=virtual_csv_file, content_type='text/csv', content_length=3)
db_entry = self.__docs_client.UploadSpreadsheet(virtual_media_source, name)
return Database(spreadsheet_entry=db_entry, database_client=self)
def GetDatabases(self, spreadsheet_key=None, name=None):
"""Finds spreadsheets which have the unique key or title.
If querying on the spreadsheet_key there will be at most one result, but
searching by name could yield multiple results.
Args:
spreadsheet_key: str The unique key for the spreadsheet, this
usually in the the form 'pk23...We' or 'o23...423.12,,,3'.
name: str The title of the spreadsheets.
Returns:
A list of Database objects representing the desired spreadsheets.
"""
if spreadsheet_key:
db_entry = self.__docs_client.GetDocumentListEntry(
r'/feeds/documents/private/full/spreadsheet%3A' + spreadsheet_key)
return [Database(spreadsheet_entry=db_entry, database_client=self)]
else:
title_query = gdata.docs.service.DocumentQuery()
title_query['title'] = name
db_feed = self.__docs_client.QueryDocumentListFeed(title_query.ToUri())
matching_databases = []
for entry in db_feed.entry:
matching_databases.append(Database(spreadsheet_entry=entry,
database_client=self))
return matching_databases
def _GetDocsClient(self):
return self.__docs_client
def _GetSpreadsheetsClient(self):
return self.__spreadsheets_client
class Database(object):
"""Provides interface to find and create tables.
The database represents a Google Spreadsheet.
"""
def __init__(self, spreadsheet_entry=None, database_client=None):
"""Constructor for a database object.
Args:
spreadsheet_entry: gdata.docs.DocumentListEntry The
Atom entry which represents the Google Spreadsheet. The
spreadsheet's key is extracted from the entry and stored as a
member.
database_client: DatabaseClient A client which can talk to the
Google Spreadsheets servers to perform operations on worksheets
within this spreadsheet.
"""
self.entry = spreadsheet_entry
if self.entry:
id_parts = spreadsheet_entry.id.text.split('/')
self.spreadsheet_key = id_parts[-1].replace('spreadsheet%3A', '')
self.client = database_client
def CreateTable(self, name, fields=None):
"""Add a new worksheet to this spreadsheet and fill in column names.
Args:
name: str The title of the new worksheet.
fields: list of strings The column names which are placed in the
first row of this worksheet. These names are converted into XML
tags by the server. To avoid changes during the translation
process I recommend using all lowercase alphabetic names. For
example ['somelongname', 'theothername']
Returns:
Table representing the newly created worksheet.
"""
worksheet = self.client._GetSpreadsheetsClient().AddWorksheet(title=name,
row_count=1, col_count=len(fields), key=self.spreadsheet_key)
return Table(name=name, worksheet_entry=worksheet,
database_client=self.client,
spreadsheet_key=self.spreadsheet_key, fields=fields)
def GetTables(self, worksheet_id=None, name=None):
"""Searches for a worksheet with the specified ID or name.
The list of results should have one table at most, or no results
if the id or name were not found.
Args:
worksheet_id: str The ID of the worksheet, example: 'od6'
name: str The title of the worksheet.
Returns:
A list of length 0 or 1 containing the desired Table. A list is returned
to make this method feel like GetDatabases and GetRecords.
"""
if worksheet_id:
worksheet_entry = self.client._GetSpreadsheetsClient().GetWorksheetsFeed(
self.spreadsheet_key, wksht_id=worksheet_id)
return [Table(name=worksheet_entry.title.text,
worksheet_entry=worksheet_entry, database_client=self.client,
spreadsheet_key=self.spreadsheet_key)]
else:
matching_tables = []
query = None
if name:
query = gdata.spreadsheet.service.DocumentQuery()
query.title = name
worksheet_feed = self.client._GetSpreadsheetsClient().GetWorksheetsFeed(
self.spreadsheet_key, query=query)
for entry in worksheet_feed.entry:
matching_tables.append(Table(name=entry.title.text,
worksheet_entry=entry, database_client=self.client,
spreadsheet_key=self.spreadsheet_key))
return matching_tables
def Delete(self):
"""Deletes the entire database spreadsheet from Google Spreadsheets."""
entry = self.client._GetDocsClient().Get(
r'http://docs.google.com/feeds/documents/private/full/spreadsheet%3A' +
self.spreadsheet_key)
self.client._GetDocsClient().Delete(entry.GetEditLink().href)
class Table(object):
def __init__(self, name=None, worksheet_entry=None, database_client=None,
spreadsheet_key=None, fields=None):
self.name = name
self.entry = worksheet_entry
id_parts = worksheet_entry.id.text.split('/')
self.worksheet_id = id_parts[-1]
self.spreadsheet_key = spreadsheet_key
self.client = database_client
self.fields = fields or []
if fields:
self.SetFields(fields)
def LookupFields(self):
"""Queries to find the column names in the first row of the worksheet.
Useful when you have retrieved the table from the server and you don't
know the column names.
"""
if self.entry:
first_row_contents = []
query = gdata.spreadsheet.service.CellQuery()
query.max_row = '1'
query.min_row = '1'
feed = self.client._GetSpreadsheetsClient().GetCellsFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, query=query)
for entry in feed.entry:
first_row_contents.append(entry.content.text)
# Get the next set of cells if needed.
next_link = feed.GetNextLink()
while next_link:
feed = self.client._GetSpreadsheetsClient().Get(next_link.href,
converter=gdata.spreadsheet.SpreadsheetsCellsFeedFromString)
for entry in feed.entry:
first_row_contents.append(entry.content.text)
next_link = feed.GetNextLink()
# Convert the contents of the cells to valid headers.
self.fields = ConvertStringsToColumnHeaders(first_row_contents)
def SetFields(self, fields):
"""Changes the contents of the cells in the first row of this worksheet.
Args:
fields: list of strings The names in the list comprise the
first row of the worksheet. These names are converted into XML
tags by the server. To avoid changes during the translation
process I recommend using all lowercase alphabetic names. For
example ['somelongname', 'theothername']
"""
# TODO: If the table already had fields, we might want to clear out the,
# current column headers.
self.fields = fields
i = 0
for column_name in fields:
i = i + 1
# TODO: speed this up by using a batch request to update cells.
self.client._GetSpreadsheetsClient().UpdateCell(1, i, column_name,
self.spreadsheet_key, self.worksheet_id)
def Delete(self):
"""Deletes this worksheet from the spreadsheet."""
worksheet = self.client._GetSpreadsheetsClient().GetWorksheetsFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id)
self.client._GetSpreadsheetsClient().DeleteWorksheet(
worksheet_entry=worksheet)
def AddRecord(self, data):
"""Adds a new row to this worksheet.
Args:
data: dict of strings Mapping of string values to column names.
Returns:
Record which represents this row of the spreadsheet.
"""
new_row = self.client._GetSpreadsheetsClient().InsertRow(data,
self.spreadsheet_key, wksht_id=self.worksheet_id)
return Record(content=data, row_entry=new_row,
spreadsheet_key=self.spreadsheet_key, worksheet_id=self.worksheet_id,
database_client=self.client)
def GetRecord(self, row_id=None, row_number=None):
"""Gets a single record from the worksheet based on row ID or number.
Args:
row_id: The ID for the individual row.
row_number: str or int The position of the desired row. Numbering
begins at 1, which refers to the second row in the worksheet since
the first row is used for column names.
Returns:
Record for the desired row.
"""
if row_id:
row_entry = self.client._GetSpreadsheetsClient().GetListFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, row_id=row_id)
return Record(content=None, row_entry=row_entry,
spreadsheet_key=self.spreadsheet_key,
worksheet_id=self.worksheet_id, database_client=self.client)
else:
row_query = gdata.spreadsheet.service.ListQuery()
row_query.start_index = str(row_number)
row_query.max_results = '1'
row_feed = self.client._GetSpreadsheetsClient().GetListFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, query=row_query)
if len(row_feed.entry) >= 1:
return Record(content=None, row_entry=row_feed.entry[0],
spreadsheet_key=self.spreadsheet_key,
worksheet_id=self.worksheet_id, database_client=self.client)
else:
return None
def GetRecords(self, start_row, end_row):
"""Gets all rows between the start and end row numbers inclusive.
Args:
start_row: str or int
end_row: str or int
Returns:
RecordResultSet for the desired rows.
"""
start_row = int(start_row)
end_row = int(end_row)
max_rows = end_row - start_row + 1
row_query = gdata.spreadsheet.service.ListQuery()
row_query.start_index = str(start_row)
row_query.max_results = str(max_rows)
rows_feed = self.client._GetSpreadsheetsClient().GetListFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, query=row_query)
return RecordResultSet(rows_feed, self.client, self.spreadsheet_key,
self.worksheet_id)
def FindRecords(self, query_string):
"""Performs a query against the worksheet to find rows which match.
For details on query string syntax see the section on sq under
http://code.google.com/apis/spreadsheets/reference.html#list_Parameters
Args:
query_string: str Examples: 'name == john' to find all rows with john
in the name column, '(cost < 19.50 and name != toy) or cost > 500'
Returns:
RecordResultSet with the first group of matches.
"""
row_query = gdata.spreadsheet.service.ListQuery()
row_query.sq = query_string
matching_feed = self.client._GetSpreadsheetsClient().GetListFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, query=row_query)
return RecordResultSet(matching_feed, self.client,
self.spreadsheet_key, self.worksheet_id)
class RecordResultSet(list):
"""A collection of rows which allows fetching of the next set of results.
The server may not send all rows in the requested range because there are
too many. Using this result set you can access the first set of results
as if it is a list, then get the next batch (if there are more results) by
calling GetNext().
"""
def __init__(self, feed, client, spreadsheet_key, worksheet_id):
self.client = client
self.spreadsheet_key = spreadsheet_key
self.worksheet_id = worksheet_id
self.feed = feed
list(self)
for entry in self.feed.entry:
self.append(Record(content=None, row_entry=entry,
spreadsheet_key=spreadsheet_key, worksheet_id=worksheet_id,
database_client=client))
def GetNext(self):
"""Fetches the next batch of rows in the result set.
Returns:
A new RecordResultSet.
"""
next_link = self.feed.GetNextLink()
if next_link and next_link.href:
new_feed = self.client._GetSpreadsheetsClient().Get(next_link.href,
converter=gdata.spreadsheet.SpreadsheetsListFeedFromString)
return RecordResultSet(new_feed, self.client, self.spreadsheet_key,
self.worksheet_id)
class Record(object):
"""Represents one row in a worksheet and provides a dictionary of values.
Attributes:
custom: dict Represents the contents of the row with cell values mapped
to column headers.
"""
def __init__(self, content=None, row_entry=None, spreadsheet_key=None,
worksheet_id=None, database_client=None):
"""Constructor for a record.
Args:
content: dict of strings Mapping of string values to column names.
row_entry: gdata.spreadsheet.SpreadsheetsList The Atom entry
representing this row in the worksheet.
spreadsheet_key: str The ID of the spreadsheet in which this row
belongs.
worksheet_id: str The ID of the worksheet in which this row belongs.
database_client: DatabaseClient The client which can be used to talk
the Google Spreadsheets server to edit this row.
"""
self.entry = row_entry
self.spreadsheet_key = spreadsheet_key
self.worksheet_id = worksheet_id
if row_entry:
self.row_id = row_entry.id.text.split('/')[-1]
else:
self.row_id = None
self.client = database_client
self.content = content or {}
if not content:
self.ExtractContentFromEntry(row_entry)
def ExtractContentFromEntry(self, entry):
"""Populates the content and row_id based on content of the entry.
This method is used in the Record's contructor.
Args:
entry: gdata.spreadsheet.SpreadsheetsList The Atom entry
representing this row in the worksheet.
"""
self.content = {}
if entry:
self.row_id = entry.id.text.split('/')[-1]
for label, custom in entry.custom.iteritems():
self.content[label] = custom.text
def Push(self):
"""Send the content of the record to spreadsheets to edit the row.
All items in the content dictionary will be sent. Items which have been
removed from the content may remain in the row. The content member
of the record will not be modified so additional fields in the row
might be absent from this local copy.
"""
self.entry = self.client._GetSpreadsheetsClient().UpdateRow(self.entry, self.content)
def Pull(self):
"""Query Google Spreadsheets to get the latest data from the server.
Fetches the entry for this row and repopulates the content dictionary
with the data found in the row.
"""
if self.row_id:
self.entry = self.client._GetSpreadsheetsClient().GetListFeed(
self.spreadsheet_key, wksht_id=self.worksheet_id, row_id=self.row_id)
self.ExtractContentFromEntry(self.entry)
def Delete(self):
self.client._GetSpreadsheetsClient().DeleteRow(self.entry)
def ConvertStringsToColumnHeaders(proposed_headers):
"""Converts a list of strings to column names which spreadsheets accepts.
When setting values in a record, the keys which represent column names must
fit certain rules. They are all lower case, contain no spaces or special
characters. If two columns have the same name after being sanitized, the
columns further to the right have _2, _3 _4, etc. appended to them.
If there are column names which consist of all special characters, or if
the column header is blank, an obfuscated value will be used for a column
name. This method does not handle blank column names or column names with
only special characters.
"""
headers = []
for input_string in proposed_headers:
# TODO: probably a more efficient way to do this. Perhaps regex.
sanitized = input_string.lower().replace('_', '').replace(
':', '').replace(' ', '')
# When the same sanitized header appears multiple times in the first row
# of a spreadsheet, _n is appended to the name to make it unique.
header_count = headers.count(sanitized)
if header_count > 0:
headers.append('%s_%i' % (sanitized, header_count+1))
else:
headers.append(sanitized)
return headers