Revision 1715
Added by Aaron Marcuse-Kubitza almost 13 years ago
| map | ||
|---|---|---|
| 224 | 224 |
|
| 225 | 225 |
in_db.close() |
| 226 | 226 |
elif in_is_xml: |
| 227 |
def get_rows(doc2rows): |
|
| 228 |
return iters.flatten(itertools.imap( |
|
| 229 |
doc2rows, xml_parse.docs_iter(sys.stdin))) |
|
| 230 |
|
|
| 227 | 231 |
if map_path == None: |
| 228 |
for in_xml_root in xml_parse.docs_iter(sys.stdin):
|
|
| 232 |
def doc2rows(in_xml_root):
|
|
| 229 | 233 |
iter_ = xml_dom.NodeElemIter(in_xml_root) |
| 230 | 234 |
util.skip(iter_, xml_dom.is_text) # skip metadata |
| 231 |
row_ct = process_rows(lambda row, i: root.appendChild(row), |
|
| 232 |
iter_) |
|
| 235 |
return iter_ |
|
| 236 |
|
|
| 237 |
row_ct = process_rows(lambda row, i: root.appendChild(row), |
|
| 238 |
get_rows(doc2rows)) |
|
| 233 | 239 |
else: |
| 234 |
def doc_rows(in_xml_root):
|
|
| 240 |
def doc2rows(in_xml_root):
|
|
| 235 | 241 |
rows = xpath.get(in_xml_root, in_root, limit=end) |
| 236 | 242 |
if rows == []: raise SystemExit('Map error: Root "'
|
| 237 | 243 |
+in_root+'" not found in input') |
| ... | ... | |
| 244 | 250 |
if nodes != []: return xml_dom.value(nodes[0]) |
| 245 | 251 |
else: return None |
| 246 | 252 |
|
| 247 |
row_ct = map_rows(get_value, iters.flatten(itertools.imap( |
|
| 248 |
doc_rows, xml_parse.docs_iter(sys.stdin)))) |
|
| 253 |
row_ct = map_rows(get_value, get_rows(doc2rows)) |
|
| 249 | 254 |
else: # input is CSV |
| 250 | 255 |
map_ = dict(mappings) |
| 251 | 256 |
reader, col_names = csvs.reader_and_header(sys.stdin) |
Also available in: Unified diff
bin/map: Extended consecutive XML document support to direct-XML inputs (without a map spreadsheet). Factored out consecutive XML document row-iteration code into helper method get_rows() which does the iters.flatten() and itertools.imap() calls.