forked from ckan/ckan
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request ckan#3390 from ckan/3390-datastore-dump-formats
datastore: dump more formats
- Loading branch information
Showing
3 changed files
with
216 additions
and
23 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,169 @@ | ||
| # encoding: utf-8 | ||
|
|
||
| from contextlib import contextmanager | ||
| from email.utils import encode_rfc2231 | ||
| import json | ||
| from xml.etree.cElementTree import Element, SubElement, ElementTree | ||
|
|
||
| import unicodecsv | ||
|
|
||
| UTF8_BOM = u'\uFEFF'.encode(u'utf-8') | ||
|
|
||
|
|
||
| @contextmanager | ||
| def csv_writer(response, fields, name=None, bom=False): | ||
| u'''Context manager for writing UTF-8 CSV data to response | ||
| :param response: file-like or response-like object for writing | ||
| data and headers (response-like objects only) | ||
| :param fields: list of datastore fields | ||
| :param name: file name (for headers, response-like objects only) | ||
| :param bom: True to include a UTF-8 BOM at the start of the file | ||
| >>> with csv_writer(response, fields) as d: | ||
| >>> d.writerow(row1) | ||
| >>> d.writerow(row2) | ||
| ''' | ||
|
|
||
| if hasattr(response, u'headers'): | ||
| response.headers['Content-Type'] = b'text/csv; charset=utf-8' | ||
| if name: | ||
| response.headers['Content-disposition'] = ( | ||
| b'attachment; filename="{name}.csv"'.format( | ||
| name=encode_rfc2231(name))) | ||
| wr = unicodecsv.writer(response, encoding=u'utf-8') | ||
| if bom: | ||
| response.write(UTF8_BOM) | ||
| wr.writerow(f['id'] for f in fields) | ||
| yield wr | ||
|
|
||
|
|
||
| @contextmanager | ||
| def tsv_writer(response, fields, name=None, bom=False): | ||
| u'''Context manager for writing UTF-8 TSV data to response | ||
| :param response: file-like or response-like object for writing | ||
| data and headers (response-like objects only) | ||
| :param fields: list of datastore fields | ||
| :param name: file name (for headers, response-like objects only) | ||
| :param bom: True to include a UTF-8 BOM at the start of the file | ||
| >>> with tsv_writer(response, fields) as d: | ||
| >>> d.writerow(row1) | ||
| >>> d.writerow(row2) | ||
| ''' | ||
|
|
||
| if hasattr(response, u'headers'): | ||
| response.headers['Content-Type'] = ( | ||
| b'text/tab-separated-values; charset=utf-8') | ||
| if name: | ||
| response.headers['Content-disposition'] = ( | ||
| b'attachment; filename="{name}.tsv"'.format( | ||
| name=encode_rfc2231(name))) | ||
| wr = unicodecsv.writer( | ||
| response, encoding=u'utf-8', dialect=unicodecsv.excel_tab) | ||
| if bom: | ||
| response.write(UTF8_BOM) | ||
| wr.writerow(f['id'] for f in fields) | ||
| yield wr | ||
|
|
||
|
|
||
| @contextmanager | ||
| def json_writer(response, fields, name=None, bom=False): | ||
| u'''Context manager for writing UTF-8 JSON data to response | ||
| :param response: file-like or response-like object for writing | ||
| data and headers (response-like objects only) | ||
| :param fields: list of datastore fields | ||
| :param name: file name (for headers, response-like objects only) | ||
| :param bom: True to include a UTF-8 BOM at the start of the file | ||
| >>> with json_writer(response, fields) as d: | ||
| >>> d.writerow(row1) | ||
| >>> d.writerow(row2) | ||
| ''' | ||
|
|
||
| if hasattr(response, u'headers'): | ||
| response.headers['Content-Type'] = ( | ||
| b'application/json; charset=utf-8') | ||
| if name: | ||
| response.headers['Content-disposition'] = ( | ||
| b'attachment; filename="{name}.json"'.format( | ||
| name=encode_rfc2231(name))) | ||
| if bom: | ||
| response.write(UTF8_BOM) | ||
| response.write( | ||
| b'{\n "fields": %s,\n "records": [' % json.dumps( | ||
| fields, ensure_ascii=False, separators=(u',', u':'))) | ||
| yield JSONWriter(response, [f['id'] for f in fields]) | ||
| response.write(b'\n]}\n') | ||
|
|
||
|
|
||
| class JSONWriter(object): | ||
| def __init__(self, response, columns): | ||
| self.response = response | ||
| self.columns = columns | ||
| self.first = True | ||
|
|
||
| def writerow(self, row): | ||
| if self.first: | ||
| self.first = False | ||
| self.response.write(b'\n ') | ||
| else: | ||
| self.response.write(b',\n ') | ||
| self.response.write(json.dumps( | ||
| row, | ||
| ensure_ascii=False, | ||
| separators=(u',', u':'), | ||
| sort_keys=True).encode(u'utf-8')) | ||
|
|
||
|
|
||
| @contextmanager | ||
| def xml_writer(response, fields, name=None, bom=False): | ||
| u'''Context manager for writing UTF-8 XML data to response | ||
| :param response: file-like or response-like object for writing | ||
| data and headers (response-like objects only) | ||
| :param fields: list of datastore fields | ||
| :param name: file name (for headers, response-like objects only) | ||
| :param bom: True to include a UTF-8 BOM at the start of the file | ||
| >>> with xml_writer(response, fields) as d: | ||
| >>> d.writerow(row1) | ||
| >>> d.writerow(row2) | ||
| ''' | ||
|
|
||
| if hasattr(response, u'headers'): | ||
| response.headers['Content-Type'] = ( | ||
| b'text/xml; charset=utf-8') | ||
| if name: | ||
| response.headers['Content-disposition'] = ( | ||
| b'attachment; filename="{name}.xml"'.format( | ||
| name=encode_rfc2231(name))) | ||
| if bom: | ||
| response.write(UTF8_BOM) | ||
| response.write(b'<data>\n') | ||
| yield XMLWriter(response, [f['id'] for f in fields]) | ||
| response.write(b'</data>\n') | ||
|
|
||
|
|
||
| class XMLWriter(object): | ||
| def __init__(self, response, columns): | ||
| self.response = response | ||
| self.id_col = columns[0] == u'_id' | ||
| if self.id_col: | ||
| columns = columns[1:] | ||
| self.columns = columns | ||
|
|
||
| def writerow(self, row): | ||
| root = Element(u'row') | ||
| if self.id_col: | ||
| root.attrib[u'_id'] = unicode(row[0]) | ||
| row = row[1:] | ||
| for k, v in zip(self.columns, row): | ||
| if v is None: | ||
| SubElement(root, k).attrib[u'xsi:nil'] = u'true' | ||
| continue | ||
| SubElement(root, k).text = unicode(v) | ||
| ElementTree(root).write(self.response, encoding=u'utf-8') | ||
| self.response.write(b'\n') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters