Created
January 7, 2018 16:22
-
-
Save rsirres/fc49afc4851e4b3026a0537c4706a05d to your computer and use it in GitHub Desktop.
Python3 XML subdocument incremental processing
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
{'country.rank': ['1'], 'country.year': ['2008'], 'country.gdppc': ['141100'], 'country.neighbor.@name': ['Austria', 'Switzerland'], 'country.neighbor.@direction': ['E', 'W'], 'country.@name': ['Liechtenstein']} | |
{'country.rank': ['4'], 'country.year': ['2011'], 'country.gdppc': ['59900'], 'country.neighbor.@name': ['Malaysia'], 'country.neighbor.@direction': ['N'], 'country.@name': ['Singapore']} | |
{'country.rank': ['68'], 'country.year': ['2011'], 'country.gdppc': ['13600'], 'country.neighbor.@name': ['Costa Rica', 'Colombia'], 'country.neighbor.@direction': ['W', 'E'], 'country.@name': ['Panama']} |
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
<?xml version="1.0"?> | |
<data> | |
<country name="Liechtenstein"> | |
<rank>1</rank> | |
<year>2008</year> | |
<gdppc>141100</gdppc> | |
<neighbor name="Austria" direction="E"/> | |
<neighbor name="Switzerland" direction="W"/> | |
</country> | |
<country name="Singapore"> | |
<rank>4</rank> | |
<year>2011</year> | |
<gdppc>59900</gdppc> | |
<neighbor name="Malaysia" direction="N"/> | |
</country> | |
<country name="Panama"> | |
<rank>68</rank> | |
<year>2011</year> | |
<gdppc>13600</gdppc> | |
<neighbor name="Costa Rica" direction="W"/> | |
<neighbor name="Colombia" direction="E"/> | |
</country> | |
</data> |
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
import xml.etree.ElementTree as ET | |
from collections import defaultdict | |
# Path to XML file | |
file_path = "/Users/Raphael/Downloads/sample4.xml" | |
# Result Container | |
result = [] | |
# XMl Namespaces Mapping the Fully Qualified Namespace to its prefix | |
# h -> http://www.w3.org/HTML/1998/html4 | |
namespaces = {} | |
# Path to current processed xml element | |
xml_path = [] | |
# Flag indicating namespace removal | |
remove_namespaces = True | |
# Given a tag name we process the xml file as a collection of subdocuments | |
subdocument_tag = "country" | |
### Helper | |
def remove_namespace(tag): | |
if "}" in tag: | |
tag = tag.split("}")[1] | |
return tag | |
def shorten_namespace(tag): | |
for k, v in namespaces.items(): | |
pass | |
def process_xml(): | |
subresult = None | |
for event, elem in ET.iterparse(file_path, events=("start-ns", "start", "end")): | |
if event == 'start': | |
tag = elem.tag | |
if tag.endswith(subdocument_tag): | |
subresult = defaultdict(list) | |
if remove_namespaces: | |
tag = remove_namespace(elem.tag) | |
# Starting tracking the path from subdocument tag | |
if tag.endswith(subdocument_tag) or subdocument_tag in xml_path: | |
xml_path.append(tag) | |
elif event == 'end': | |
# process the tag | |
if elem.tag.endswith(subdocument_tag): | |
result.append( subresult ) | |
#continue | |
if elem.text and elem.text.strip(): | |
key = ".".join(xml_path) | |
subresult[key].append(elem.text) | |
if elem.attrib: | |
prefix = ".".join(xml_path) | |
for attribute, value in elem.attrib.items(): | |
key = prefix + ".@" + attribute | |
subresult[key].append(value) | |
# Starting tracking the path from subdocument tag | |
if tag.endswith(subdocument_tag) or subdocument_tag in xml_path: | |
xml_path.pop() | |
# Delete SubDocument when processing is done | |
if subdocument_tag and elem.tag.endswith(subdocument_tag): | |
elem.clear() | |
elif event == "start-ns": | |
namespaces[ "{" + elem[1] + "}"] = elem[0] | |
process_xml() | |
# Print Namespaces | |
for k, v in namespaces.items(): | |
print(k, " ", v) | |
# Print Result | |
for item in result: | |
print( dict(item) ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment