Revision 164
Added by Aaron Marcuse-Kubitza about 13 years ago
| scripts/test/accepted_output/NYBG.organisms.VegBank.xml | ||
|---|---|---|
| 1 | 1 |
<?xml version="1.0" ?> |
| 2 | 2 |
<VegBank> |
| 3 | 3 |
<taxonObservation id="0"> |
| 4 |
<taxonImportance> |
|
| 5 |
<stemCount> |
|
| 6 |
<stemCount>1</stemCount> |
|
| 7 |
<stemLocation> |
|
| 8 |
<definedValue fkey="tableRecord_ID"> |
|
| 9 |
<userDefined_ID> |
|
| 10 |
<userDefined> |
|
| 11 |
<tableName>stemLocation</tableName> |
|
| 12 |
<userDefinedName>habitat</userDefinedName> |
|
| 13 |
<userDefinedType>varchar</userDefinedType> |
|
| 14 |
</userDefined> |
|
| 15 |
</userDefined_ID> |
|
| 16 |
<definedValue>Floodplain forest</definedValue> |
|
| 17 |
</definedValue> |
|
| 18 |
<definedValue fkey="tableRecord_ID"> |
|
| 19 |
<userDefined_ID> |
|
| 20 |
<userDefined> |
|
| 21 |
<tableName>stemLocation</tableName> |
|
| 22 |
<userDefinedName>plantFungusDescription</userDefinedName> |
|
| 23 |
<userDefinedType>varchar</userDefinedType> |
|
| 24 |
</userDefined> |
|
| 25 |
</userDefined_ID> |
|
| 26 |
<definedValue>with rough brown bark, almost no buttressing, 1 m diam; fallen fruit and leaves</definedValue> |
|
| 27 |
</definedValue> |
|
| 28 |
</stemLocation> |
|
| 29 |
</stemCount> |
|
| 30 |
</taxonImportance> |
|
| 31 | 4 |
<observation_ID> |
| 32 | 5 |
<observation> |
| 33 | 6 |
<plot_ID> |
| ... | ... | |
| 68 | 41 |
<obsStartDate>1984-08-20</obsStartDate> |
| 69 | 42 |
</observation> |
| 70 | 43 |
</observation_ID> |
| 44 |
<taxonImportance> |
|
| 45 |
<stemCount> |
|
| 46 |
<stemCount>1</stemCount> |
|
| 47 |
<stemLocation> |
|
| 48 |
<definedValue fkey="tableRecord_ID"> |
|
| 49 |
<userDefined_ID> |
|
| 50 |
<userDefined> |
|
| 51 |
<tableName>stemLocation</tableName> |
|
| 52 |
<userDefinedName>habitat</userDefinedName> |
|
| 53 |
<userDefinedType>varchar</userDefinedType> |
|
| 54 |
</userDefined> |
|
| 55 |
</userDefined_ID> |
|
| 56 |
<definedValue>Floodplain forest</definedValue> |
|
| 57 |
</definedValue> |
|
| 58 |
<definedValue fkey="tableRecord_ID"> |
|
| 59 |
<userDefined_ID> |
|
| 60 |
<userDefined> |
|
| 61 |
<tableName>stemLocation</tableName> |
|
| 62 |
<userDefinedName>plantFungusDescription</userDefinedName> |
|
| 63 |
<userDefinedType>varchar</userDefinedType> |
|
| 64 |
</userDefined> |
|
| 65 |
</userDefined_ID> |
|
| 66 |
<definedValue>with rough brown bark, almost no buttressing, 1 m diam; fallen fruit and leaves</definedValue> |
|
| 67 |
</definedValue> |
|
| 68 |
</stemLocation> |
|
| 69 |
</stemCount> |
|
| 70 |
</taxonImportance> |
|
| 71 | 71 |
<taxonInterpretation> |
| 72 | 72 |
<ROLE_ID> |
| 73 | 73 |
<aux_Role> |
| ... | ... | |
| 315 | 315 |
</taxonInterpretation> |
| 316 | 316 |
</taxonObservation> |
| 317 | 317 |
<taxonObservation id="1"> |
| 318 |
<taxonImportance> |
|
| 319 |
<stemCount> |
|
| 320 |
<stemCount>1</stemCount> |
|
| 321 |
</stemCount> |
|
| 322 |
</taxonImportance> |
|
| 323 | 318 |
<observation_ID> |
| 324 | 319 |
<observation> |
| 325 | 320 |
<plot_ID> |
| ... | ... | |
| 352 | 347 |
<obsStartDate>1994-01-17</obsStartDate> |
| 353 | 348 |
</observation> |
| 354 | 349 |
</observation_ID> |
| 350 |
<taxonImportance> |
|
| 351 |
<stemCount> |
|
| 352 |
<stemCount>1</stemCount> |
|
| 353 |
</stemCount> |
|
| 354 |
</taxonImportance> |
|
| 355 | 355 |
<taxonInterpretation> |
| 356 | 356 |
<ROLE_ID> |
| 357 | 357 |
<aux_Role> |
| scripts/map | ||
|---|---|---|
| 16 | 16 |
import xml_func |
| 17 | 17 |
|
| 18 | 18 |
def metadata_value(name): |
| 19 |
if name.startswith(':'): return name[1:]
|
|
| 19 |
if type(name) == str and name.startswith(':'): return name[1:]
|
|
| 20 | 20 |
else: return None |
| 21 | 21 |
|
| 22 | 22 |
def main(): |
| ... | ... | |
| 66 | 66 |
for row in reader: |
| 67 | 67 |
in_, out = row[:2] |
| 68 | 68 |
if out != '': |
| 69 |
value = metadata_value(in_) |
|
| 70 |
if out_is_xpaths: out = xpath.parse(out_root+out) |
|
| 71 |
if value != None: metadata.append((value, out)) |
|
| 72 |
else: mappings.append((in_, out)) |
|
| 69 |
if out_is_xpaths: out = out_root+out |
|
| 70 |
mappings.append((in_, out)) |
|
| 73 | 71 |
stream.close() |
| 74 | 72 |
in_is_xml = in_is_xpaths and not in_is_db |
| 75 | 73 |
|
| ... | ... | |
| 85 | 83 |
import db_xml |
| 86 | 84 |
|
| 87 | 85 |
in_root_xml = xpath.path2xml(in_root) |
| 88 |
mappings = [(xpath.path2xml(in_root+in_), out) for in_, out in mappings] |
|
| 86 |
for i, mapping in enumerate(mappings): |
|
| 87 |
in_, out = mapping |
|
| 88 |
if metadata_value(in_) == None: |
|
| 89 |
mappings[i] = (xpath.path2xml(in_root+in_), out) |
|
| 89 | 90 |
|
| 90 | 91 |
in_db = sql.connect(in_db_config) |
| 91 | 92 |
in_pkeys = {}
|
| ... | ... | |
| 93 | 94 |
limit)): |
| 94 | 95 |
row_id, = row |
| 95 | 96 |
row_id = str(row_id) |
| 96 |
|
|
| 97 |
def put_col(path, value): |
|
| 98 |
xpath.put_obj(root, path, row_id, has_types, value) |
|
| 99 |
for value, out in metadata: put_col(out, value) |
|
| 100 | 97 |
for in_, out in mappings: |
| 101 |
in_ = in_.cloneNode(True) # don't modify orig value! |
|
| 102 |
xml_dom.set_id(xpath.get(in_, in_root), row_id) |
|
| 103 |
value = sql.value_or_none(db_xml.get(in_db, in_, in_pkeys)) |
|
| 104 |
if value != None: put_col(out, str(value)) |
|
| 98 |
value = metadata_value(in_) |
|
| 99 |
if value == None: |
|
| 100 |
in_ = in_.cloneNode(True) # don't modify orig value! |
|
| 101 |
xml_dom.set_id(xpath.get(in_, in_root), row_id) |
|
| 102 |
value = sql.value_or_none(db_xml.get(in_db, in_, |
|
| 103 |
in_pkeys)) |
|
| 104 |
if value != None: |
|
| 105 |
xpath.put_obj(root, out, row_id, has_types, str(value)) |
|
| 105 | 106 |
in_db.close() |
| 106 | 107 |
elif in_is_xml: |
| 107 | 108 |
row = xpath.get(doc0.documentElement, in_root) |
| 108 | 109 |
for row_idx, row in enumerate(xml_dom.NodeElemIter(row.parentNode)): |
| 109 | 110 |
if not (limit == None or row_idx < limit): break |
| 110 | 111 |
row_id = str(row_idx) |
| 111 |
|
|
| 112 |
def put_col(path, value): |
|
| 113 |
xpath.put_obj(root, path, row_id, has_types, value) |
|
| 114 |
for value, out in metadata: put_col(out, value) |
|
| 115 | 112 |
for in_, out in mappings: |
| 116 |
node = xpath.get(row, in_) |
|
| 117 |
if node != None: put_col(out, xml_dom.value(node)) |
|
| 113 |
value = metadata_value(in_) |
|
| 114 |
if value == None: |
|
| 115 |
node = xpath.get(row, in_) |
|
| 116 |
if node != None: value = xml_dom.value(node) |
|
| 117 |
if value != None: |
|
| 118 |
xpath.put_obj(root, out, row_id, has_types, value) |
|
| 118 | 119 |
else: # input is CSV |
| 119 | 120 |
map_ = dict(mappings) |
| 120 | 121 |
reader = csv.reader(sys.stdin) |
| 121 | 122 |
cols = reader.next() |
| 122 | 123 |
col_idxs = dict([(value, idx) for idx, value in enumerate(cols)]) |
| 123 |
mappings = [(col_idxs.get(in_, None), out) for in_, out in mappings] |
|
| 124 |
mappings = filter(lambda item: item[0] != None, mappings) |
|
| 124 |
for i, mapping in enumerate(mappings): |
|
| 125 |
in_, out = mapping |
|
| 126 |
if metadata_value(in_) == None: |
|
| 127 |
try: mappings[i] = (col_idxs[in_], out) |
|
| 128 |
except KeyError: pass |
|
| 125 | 129 |
|
| 126 | 130 |
for row_idx, row in enumerate(reader): |
| 127 | 131 |
if not (limit == None or row_idx < limit): break |
| 128 | 132 |
row_id = str(row_idx) |
| 129 |
|
|
| 130 |
def put_col(path, value): |
|
| 131 |
xpath.put_obj(root, path, row_id, has_types, value) |
|
| 132 |
for value, out in metadata: put_col(out, value) |
|
| 133 | 133 |
for in_, out in mappings: |
| 134 |
if row[in_] != '': put_col(out, row[in_]) |
|
| 134 |
value = metadata_value(in_) |
|
| 135 |
if value == None: |
|
| 136 |
value = row[in_] |
|
| 137 |
if value == '': value = None |
|
| 138 |
if value != None: |
|
| 139 |
xpath.put_obj(root, out, row_id, has_types, value) |
|
| 135 | 140 |
xml_func.process(root) |
| 136 | 141 |
else: doc1 = doc0 |
| 137 | 142 |
|
Also available in: Unified diff
map: Handle metadata in order with regular mappings