Related
This question already has answers here:
What are type hints in Python 3.5?
(5 answers)
What does -> mean in Python function definitions?
(11 answers)
Closed 2 years ago.
i am using python 3.7 and i have just started my own opensource project. Some time ago a very skilled software developer decided to help, then he didn't have enough time to continue. So i am taking his work back to develop new features for the project. Now he has designed a script to manage the reading of text from pdf and doc files. He has developed it very well but there is something i don't understand:
#classmethod
def extract_document_data(cls, file_path : str) -> DocumentData:
"""
Entry point of the module, it extracts the data from the document
whose path is passed as input.
The extraction strategy is automatically chosen based on the MIME type
of the file.
#type file_path: str
#param file_path: The path of the document to be parsed.
#rtype: DocumentData
#returns: An object containing the data of the parsed document.
"""
mime = magic.Magic(mime=True)
mime_type = mime.from_file(file_path)
document_type = DocumentType.get_instance(mime_type)
strategy = cls.strategies[document_type]
return strategy.extract_document_data(file_path)
this: -> DocumentData is very obscure for me, as if it was a lamdba it shouls be included in the methods arguments as a callback doesn't it? which meaning does it have in this position?
I can paste even the whole classe if you need a more verbose insight:
from enum import Enum
import json
import magic
import docx
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTContainer, LTTextContainer
from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfparser import PDFParser
class DocumentType(Enum):
"""
Defines the handled document types.
Each value is associated to a MIME type.
"""
def __init__(self, mime_type):
self.mime_type = mime_type
#classmethod
def get_instance(cls, mime_type : str):
values = [e for e in cls]
for value in values:
if value.mime_type == mime_type:
return value
raise MimeNotValidError(mime_type)
PDF = 'application/pdf'
DOCX = 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
class MimeNotValidError(Exception):
"""
Exception to be raised when a not valid MIME type is processed.
"""
pass
class DocumentData:
"""
Wrapper for the extracted document data (TOC and contents).
"""
def __init__(self, toc : list = [], pages : list = [], document_text : str = None):
self.toc = toc
self.pages = pages
if document_text is not None:
self.document_text = document_text
else:
self.document_text = ' '.join([page.replace('\n', ' ') for page in pages])
def toc_as_json(self) -> str:
return json.dumps(self.toc)
class ExtractionStrategy:
"""
Base class for the extraction strategies.
"""
#staticmethod
def extract_document_data(file_path : str) -> DocumentData:
pass
class DOCXExtractionStrategy(ExtractionStrategy):
"""
It implements the TOC and contents extraction from a DOCX document.
"""
#staticmethod
def extract_document_data(file_path : str) -> DocumentData:
document = docx.Document(file_path)
body_elements = document._body._body
# Selecting only the <w:t> elements from DOCX XML,
# as they're the only to contain some text.
text_elems = body_elements.xpath('.//w:t')
return DocumentData(document_text = ' '.join([elem.text for elem in text_elems]))
class PDFExtractionStrategy(ExtractionStrategy):
"""
It implements the TOC and contents extraction from a PDF document.
"""
#staticmethod
def parse_toc(doc : PDFDocument) -> list:
raw_toc = []
try:
outlines = doc.get_outlines()
for (level, title, dest, a, se) in outlines:
raw_toc.append((level, title))
except PDFNoOutlines:
pass
return PDFExtractionStrategy.build_toc_tree(raw_toc)
#staticmethod
def build_toc_tree(items : list) -> list:
"""
Builds the TOC tree from a list of TOC items.
#type items: list
#param items: The TOC items.
Each item must have the following format: (<item depth>, <item description>).
E.g: [(1, 'Contents'), (2, 'Chapter 1'), (2, 'Chapter 2')]
#rtype: list
#returns: The TOC tree. The tree hasn't a root element, therefore it
actually is a list.
"""
toc = []
if items is None or len(items) == 0:
return toc
current_toc_level = toc
# Using an explicit stack containing the lists corresponding to
# the various levels of the TOC, to simulate the recursive building
# of the TOC tree in a more efficient way
toc_levels_stack = []
toc_levels_stack.append(current_toc_level)
# Each TOC item can be inserted into the current TOC level as
# string (just the item description) or as dict, where the key is
# the item description and the value is a list containing the
# children TOC items.
# To correctly determine how to insert the current item into
# the current level, a kind of look-ahead is needed, that is
# the depth of the next item has to be considered.
# Initializing the variables related to the previous item.
prev_item_depth, prev_item_desc = items[0]
# Adding a fake final item in order to handle all the TOC items
# inside the cycle.
items.append((-1, ''))
for i in range(1, len(items)):
# In fact each iteration handles the item of the previous
# one, using the current item to determine how to insert
# the previous item into the current TOC level,
# as explained before.
curr_item = items[i]
curr_item_depth = curr_item[0]
if curr_item_depth == prev_item_depth:
# The depth of the current item is the same
# as the previous one.
# Inserting the previous item into the current TOC level
# as string.
current_toc_level.append(prev_item_desc)
elif curr_item_depth == prev_item_depth + 1:
# The depth of the current item is increased by 1 compared to
# the previous one.
# Inserting the previous item into the current TOC level
# as dict.
prev_item_dict = { prev_item_desc : [] }
current_toc_level.append(prev_item_dict)
# Updating the current TOC level with the newly created one
# which contains the children of the previous item.
current_toc_level = prev_item_dict[prev_item_desc]
toc_levels_stack.append(current_toc_level)
elif curr_item_depth < prev_item_depth:
# The depth of the current item is lesser than
# the previous one.
# Inserting the previous item into the current TOC level
# as string.
current_toc_level.append(prev_item_desc)
if i < len(items)-1:
# Executing these steps for all the items except the last one
depth_diff = prev_item_depth - curr_item_depth
# Removing from the stack as many TOC levels as the difference
# between the depth of the previous item and the depth of the
# current one.
for i in range(0, depth_diff):
toc_levels_stack.pop()
# Updating the current TOC level with the one contained in
# the head of the stack.
current_toc_level = toc_levels_stack[-1]
# Updating the previous item with the current one
prev_item_depth, prev_item_desc = curr_item
return toc
#staticmethod
def from_bytestring(s) -> str:
"""
If the input string is a byte-string, converts it to a string using
UTF-8 as encoding.
#param s: A string or a byte-string.
#rtype: str
#returns: The potentially converted string.
"""
if s:
if isinstance(s, str):
return s
else:
return s.encode('utf-8')
#staticmethod
def parse_layout_nodes(container : LTContainer) -> str:
"""
Recursively extracts the text from all the nodes contained in the
input PDF layout tree/sub-tree.
#type container: LTContainer
#param container: The PDF layout tree/sub-tree from which to extract the text.
#rtype: str
#returns: A string containing the extracted text.
"""
text_content = []
# The iterator returns the children nodes.
for node in container:
if isinstance(node, LTTextContainer):
# Only nodes of type LTTextContainer contain text.
text_content.append(PDFExtractionStrategy.from_bytestring(node.get_text()))
elif isinstance(node, LTContainer):
# Recursively calling the method on the current node, which is a container itself.
text_content.append(PDFExtractionStrategy.parse_layout_nodes(node))
else:
# Ignoring all the other node types.
pass
# Joining all the extracted text chunks with a new line character.
return "\n".join(text_content)
#staticmethod
def parse_pages(doc : PDFDocument) -> list:
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
text_content = []
for i, page in enumerate(PDFPage.create_pages(doc)):
interpreter.process_page(page)
layout = device.get_result()
# Extracts the text from all the nodes of the PDF layout tree of each page
text_content.append(PDFExtractionStrategy.parse_layout_nodes(layout))
return text_content
#staticmethod
def parse_pdf(file_path : str) -> (list, list):
toc = []
pages = []
try:
fp = open(file_path, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser)
parser.set_document(doc)
if doc.is_extractable:
toc = PDFExtractionStrategy.parse_toc(doc)
pages = PDFExtractionStrategy.parse_pages(doc)
fp.close()
except IOError:
pass
return (toc, pages)
#staticmethod
def extract_document_data(file_path : str) -> DocumentData:
toc, pages = PDFExtractionStrategy.parse_pdf(file_path)
return DocumentData(toc, pages = pages)
class DocumentDataExtractor:
"""
Main class of the module.
It's responsible for actually executing the text extraction.
The output is constituted by the following items:
-table of contents (TOC);
-pages contents.
"""
# Dictionary containing the extraction strategies for the different
# document types, indexed by the corresponding DocumentType enum values.
strategies = {
DocumentType.DOCX : DOCXExtractionStrategy(),
DocumentType.PDF : PDFExtractionStrategy()
}
#classmethod
def extract_document_data(cls, file_path : str) -> DocumentData:
"""
Entry point of the module, it extracts the data from the document
whose path is passed as input.
The extraction strategy is automatically chosen based on the MIME type
of the file.
#type file_path: str
#param file_path: The path of the document to be parsed.
#rtype: DocumentData
#returns: An object containing the data of the parsed document.
"""
mime = magic.Magic(mime=True)
mime_type = mime.from_file(file_path)
document_type = DocumentType.get_instance(mime_type)
strategy = cls.strategies[document_type]
return strategy.extract_document_data(file_path)
I am new to programming in python,´and i have some troubles understanding the concept. I wish to compare two xml files. These xml files are quite large.
I will give an example for the type of files i wish to compare.
xmlfile1:
<xml>
<property1>
<property2>
<property3>
</property3>
</property2>
</property1>
</xml>
xml file2:
<xml>
<property1>
<property2>
<property3>
<property4>
</property4>
</property3>
</property2>
</property1>
</xml>
the property1,property2 that i have named are different from the ones that are actually in the file. There are a lot of properties within the xml file.
ANd i wish to compare the two xml files.
I am using an lxml parser to try to compare the two files and to print out the difference between them.
I do not know how to parse it and compare it automatically.
I tried reading through the lxml parser, but i couldnt understand how to use it to my problem.
Can someone please tell me how should i proceed with this problem.
Code snippets can be very useful
One more question, Am i following the right concept or i am missing something else? Please correct me of any new concepts that you knwo about
This is actually a reasonably challenging problem (due to what "difference" means often being in the eye of the beholder here, as there will be semantically "equivalent" information that you probably don't want marked as differences).
You could try using xmldiff, which is based on work in the paper Change Detection in Hierarchically Structured Information.
My approach to the problem was transforming each XML into a xml.etree.ElementTree and iterating through each of the layers.
I also included the functionality to ignore a list of attributes while doing the comparison.
The first block of code holds the class used:
import xml.etree.ElementTree as ET
import logging
class XmlTree():
def __init__(self):
self.hdlr = logging.FileHandler('xml-comparison.log')
self.formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
#staticmethod
def convert_string_to_tree( xmlString):
return ET.fromstring(xmlString)
def xml_compare(self, x1, x2, excludes=[]):
"""
Compares two xml etrees
:param x1: the first tree
:param x2: the second tree
:param excludes: list of string of attributes to exclude from comparison
:return:
True if both files match
"""
if x1.tag != x2.tag:
self.logger.debug('Tags do not match: %s and %s' % (x1.tag, x2.tag))
return False
for name, value in x1.attrib.items():
if not name in excludes:
if x2.attrib.get(name) != value:
self.logger.debug('Attributes do not match: %s=%r, %s=%r'
% (name, value, name, x2.attrib.get(name)))
return False
for name in x2.attrib.keys():
if not name in excludes:
if name not in x1.attrib:
self.logger.debug('x2 has an attribute x1 is missing: %s'
% name)
return False
if not self.text_compare(x1.text, x2.text):
self.logger.debug('text: %r != %r' % (x1.text, x2.text))
return False
if not self.text_compare(x1.tail, x2.tail):
self.logger.debug('tail: %r != %r' % (x1.tail, x2.tail))
return False
cl1 = x1.getchildren()
cl2 = x2.getchildren()
if len(cl1) != len(cl2):
self.logger.debug('children length differs, %i != %i'
% (len(cl1), len(cl2)))
return False
i = 0
for c1, c2 in zip(cl1, cl2):
i += 1
if not c1.tag in excludes:
if not self.xml_compare(c1, c2, excludes):
self.logger.debug('children %i do not match: %s'
% (i, c1.tag))
return False
return True
def text_compare(self, t1, t2):
"""
Compare two text strings
:param t1: text one
:param t2: text two
:return:
True if a match
"""
if not t1 and not t2:
return True
if t1 == '*' or t2 == '*':
return True
return (t1 or '').strip() == (t2 or '').strip()
The second block of code holds a couple of XML examples and their comparison:
xml1 = "<note><to>Tove</to><from>Jani</from><heading>Reminder</heading><body>Don't forget me this weekend!</body></note>"
xml2 = "<note><to>Tove</to><from>Daniel</from><heading>Reminder</heading><body>Don't forget me this weekend!</body></note>"
tree1 = XmlTree.convert_string_to_tree(xml1)
tree2 = XmlTree.convert_string_to_tree(xml2)
comparator = XmlTree()
if comparator.xml_compare(tree1, tree2, ["from"]):
print "XMLs match"
else:
print "XMLs don't match"
Most of the credit for this code must be given to syawar
If your intent is to compare the XML content and attributes, and not just compare the files byte-by-byte, there are subtleties to the question, so there is no solution that fits all cases.
You have to know something about what is important in the XML files.
The order of attributes listed in an element tag is generally not supposed to matter. That is, two XML files that differ only in the order of element attributes generally ought to be judged the same.
But that's the generic part.
The tricky part is application-dependent. For instance, it may be that white-space formatting of some elements of the file doesn't matter, and white-space might be added to the XML for legibility. And so on.
Recent versions of the ElementTree module have a function canonicalize(), which can take care of simpler cases, by putting the XML string into a canonical format.
I used this function in the unit tests of a recent project, to compare a known XML output with output from a package that sometimes changes the order of attributes. In this case, white space in the text elements was unimportant, but it was sometimes used for formatting.
import xml.etree.ElementTree as ET
def _canonicalize_XML( xml_str ):
""" Canonicalizes XML strings, so they are safe to
compare directly.
Strips white space from text content."""
if not hasattr( ET, "canonicalize" ):
raise Exception( "ElementTree missing canonicalize()" )
root = ET.fromstring( xml_str )
rootstr = ET.tostring( root )
return ET.canonicalize( rootstr, strip_text=True )
To use it, something like this:
file1 = ET.parse('file1.xml')
file2 = ET.parse('file2.xml')
canon1 = _canonicalize_XML( ET.tostring( file1.getroot() ) )
canon2 = _canonicalize_XML( ET.tostring( file2.getroot() ) )
print( canon1 == canon2 )
In my distribution, the Python 2 doesn't have canonicalize(), but Python 3 does.
Another script using xml.etree. Its awful but it works :)
#!/usr/bin/env python
import sys
import xml.etree.ElementTree as ET
from termcolor import colored
tree1 = ET.parse(sys.argv[1])
root1 = tree1.getroot()
tree2 = ET.parse(sys.argv[2])
root2 = tree2.getroot()
class Element:
def __init__(self,e):
self.name = e.tag
self.subs = {}
self.atts = {}
for child in e:
self.subs[child.tag] = Element(child)
for att in e.attrib.keys():
self.atts[att] = e.attrib[att]
print "name: %s, len(subs) = %d, len(atts) = %d" % ( self.name, len(self.subs), len(self.atts) )
def compare(self,el):
if self.name!=el.name:
raise RuntimeError("Two names are not the same")
print "----------------------------------------------------------------"
print self.name
print "----------------------------------------------------------------"
for att in self.atts.keys():
v1 = self.atts[att]
if att not in el.atts.keys():
v2 = '[NA]'
color = 'yellow'
else:
v2 = el.atts[att]
if v2==v1:
color = 'green'
else:
color = 'red'
print colored("first:\t%s = %s" % ( att, v1 ), color)
print colored("second:\t%s = %s" % ( att, v2 ), color)
for subName in self.subs.keys():
if subName not in el.subs.keys():
print colored("first:\thas got %s" % ( subName), 'purple')
print colored("second:\thasn't got %s" % ( subName), 'purple')
else:
self.subs[subName].compare( el.subs[subName] )
e1 = Element(root1)
e2 = Element(root2)
e1.compare(e2)
I'm using the following code as a portion of a larger program that does some error checking on a Digital Cinema Package and tries to check the validity of the XML file that lists the asses on the DCP. ANyway, this is all still very much in its infancy and I'm hoping to learn more python as a result of it.
import xml.etree.ElementTree as etree
import sys
class Parser(object):
def __init__(self, file_name):
self.file_name = file_name
def display(self, rename_this_list):
tree = etree.parse(self.file_name)
for node in tree.getiterator():
for element in rename_this_list:
if element in node.tag:
uuid=(node.text)
#uuid = [s.strip('urn:') for s in uuid]
print(uuid)
fname = sys.argv[1]
key_search_words = ['KeyId']
instance = Parser(fname)
instance.display(key_search_words)
when I try to store the output so that each line is a list it doesn't format the way that I would expect. Minus the urn: I'd like to be storing each line with uuid: and the following info as an element of a list.
urn:uuid:9851b0f6-4790-0d4c-a69d-ea8abdedd03d
urn:uuid:8317e8f3-1597-494d-9ed8-08a751ff8615
urn:uuid:5d9b228d-7120-344c-aefc-840cdd32bbfc
urn:uuid:1e32ccb2-ab0b-9d43-b879-1c12840c178b
urn:uuid:44d04416-676a-2e4f-8995-165de8cab78d
urn:uuid:906da0c1-b0cb-4541-b8a9-86476583cdc4
urn:uuid:0fe2d73a-ebe3-9844-b3de-4517c63c4b90
urn:uuid:862fa79a-18c7-9245-a172-486541bef0c0
urn:uuid:aa2f1a88-7a55-894d-bc19-42afca589766
urn:uuid:59d6eeff-cd56-6245-9f13-951554466626
urn:uuid:14a13b1a-76ba-764c-97d0-9900f58af53e
urn:uuid:ccdbe0ae-1c3f-224c-b450-947f43bbd640
urn:uuid:dcd37f10-b042-8e44-bef0-89bda2174842
urn:uuid:9dd7103e-7e5a-a840-a15f-f7d7fe699203
If you need a list, then you can try this.
def display(self, rename_this_list):
listOfNodes = []
tree = etree.parse(self.file_name)
for node in tree.getiterator():
for element in rename_this_list:
if element in node.tag:
# append text of element to the list
# without first four characters which are "urn:"
listOfNodes.append(node.text[4:])
print str(listOfNodes)
return listOfNodes
Remember that keys of a dictionary have to be unique, in a dictionary you can't have two items with keys "uuid", if you want a dictionary then you can only have one dictionary with one key "uuid" and a list of all those numbers as values.
import collections
class Parser(object):
def __init__(self, file_name):
self.file_name = file_name, self.res = collections.defaultdict(list)
def display(self, rename_this_list):
tree = etree.parse(self.file_name)
for node in tree.getiterator():
for element in rename_this_list:
if element in node.tag:
uuid = node.text
key, value = uuid[4:].split(':')
self.res[key].append(value)
Can this satisfy your need? I don't know the details of your data so if anything wrong please tell. I think the result should be like this:
{'uuid':['9851b0f6-4790-0d4c-a69d-ea8abdedd03d','ccdbe0ae-1c3f-224c-b450-947f43bbd640',...]}
I'd like to parse and compare 2 XML files with the Python Etree parser as follows:
I have 2 XML files with loads of data. One is in English (the source file), the other one the corresponding French translation (the target file).
E.g.:
source file:
<AB>
<CD/>
<EF>
<GH>
<id>123</id>
<IJ>xyz</IJ>
<KL>DOG</KL>
<MN>dogs/dog</MN>
some more tags and info on same level
<metadata>
<entry>
<cl>Translation</cl>
<cl>English:dog/dogs</cl>
</entry>
<entry>
<string>blabla</string>
<string>blabla</string>
</entry>
some more strings and entries
</metadata>
</GH>
</EF>
<stuff/>
<morestuff/>
<otherstuff/>
<stuffstuff/>
<blubb/>
<bla/>
<blubbbla>8</blubbla>
</AB>
The target file looks exactly the same, but has no text at some places:
<MN>chiens/chien</MN>
some more tags and info on same level
<metadata>
<entry>
<cl>Translation</cl>
<cl></cl>
</entry>
The French target file has an empty cross-language reference where I'd like to put in the information from the English source file whenever the 2 macros have the same ID.
I already wrote some code in which I replaced the string tag name with a unique tag name in order to identify the cross-language reference. Now I want to compare the 2 files and if 2 macros have the same ID, exchange the empty reference in the French file with the info from the English file. I was trying out the minidom parser before but got stuck and would like to try Etree now. I have hardly any knowledge about programming and find this very hard.
Here is the code I have so far:
macros = ElementTree.parse(english)
for tag in macros.getchildren('macro'):
id_ = tag.find('id')
data = tag.find('cl')
id_dict[id_.text] = data.text
macros = ElementTree.parse(french)
for tag in macros.getchildren('macro'):
id_ = tag.find('id')
target = tag.find('cl')
if target.text.strip() == '':
target.text = id_dict[id_.text]
print (ElementTree.tostring(macros))
I am more than clueless and reading other posts on this confuses me even more. I'd appreciate it very much if someone could enlighten me :-)
There is probably more details to be clarified. Here is the sample with some debug prints that shows the idea. It assumes that both files have exactly the same structure, and that you want to go only one level below the root:
import xml.etree.ElementTree as etree
english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')
# Get the root elements, as they support iteration
# through their children (direct descendants)
english_root = english_tree.getroot()
french_root = french_tree.getroot()
# Iterate through the direct descendants of the root
# elements in both trees in parallel.
for en, fr in zip(english_root, french_root):
assert en.tag == fr.tag # check for the same structure
if en.tag == 'id':
assert en.text == fr.text # check for the same id
elif en.tag == 'string':
if fr.text is None:
fr.text = en.text
print en.text # displaying what was replaced
etree.dump(french_tree)
For more complex structures of the file, the loop through the direct children of the node can be replaced by iteration through all the elements of the tree. If the structures of the files are exactly the same, the following code will work:
import xml.etree.ElementTree as etree
english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')
for en, fr in zip(english_tree.iter(), french_tree.iter()):
assert en.tag == fr.tag # check if the structure is the same
if en.tag == 'id':
assert en.text == fr.text # identification must be the same
elif en.tag == 'string':
if fr.text is None:
fr.text = en.text
print en.text # display the inserted text
# Write the result to the output file.
with open('fr2.xml', 'w') as fout:
fout.write(etree.tostring(french_tree.getroot()))
However, it works only in cases when both files have exactly the same structure. Let's follow the algorithm that would be used when the task is to be done manually. Firstly, we need to find the French translation that is empty. Then it should be replaced by the English translation from the GH element with the same identification. A subset of XPath expressions is used in the case when searching for the elements:
import xml.etree.ElementTree as etree
def find_translation(tree, id_):
# Search fot the GH element with the given identification, and return
# its translation if found. Otherwise None is returned implicitly.
for gh in tree.iter('GH'):
id_elem = gh.find('./id')
if id_ == id_elem.text:
# The related GH element found.
# Find metadata entry, extract the translation.
# Warning! This is simplification for the fixed position
# of the Translation entry.
me = gh.find('./metadata/entry')
assert len(me) == 2 # metadata/entry has two elements
cl1 = me[0]
assert cl1.text == 'Translation'
cl2 = me[1]
return cl2.text
# Body of the program. --------------------------------------------------
english_tree = etree.parse('en.xml')
french_tree = etree.parse('fr.xml')
for gh in french_tree.iter('GH'): # iterate through the GH elements only
# Get the identification of the GH section
id_elem = gh.find('./id')
id_ = id_elem.text
# Find and check the metadata entry, extract the French translation.
# Warning! This is simplification for the fixed position of the Translation
# entry.
me = gh.find('./metadata/entry')
assert len(me) == 2 # metadata/entry has two elements
cl1 = me[0]
assert cl1.text == 'Translation'
cl2 = me[1]
fr_translation = cl2.text
# If the French translation is empty, put there the English translation
# from the related element.
if cl2.text is None:
cl2.text = find_translation(english_tree, id_)
with open('fr2.xml', 'w') as fout:
fout.write(etree.tostring(french_tree.getroot()).decode('utf-8'))
Is there a way to parse a file which contains multiple xmls in it?
eg., if I have a file called stocks.xml and within the stocks.xml i have more than one xml content, is there any way to parse this xml file ?.
-- stocks.xml
<?xml version="1.0" encoding="ASCII"?><PRODUCT><ID>A001</ID>..</PRODUCT><SHOP-1><QUANTITY>nn</QUANITY><SHOP-1><QUANTITY>nn</QUANITY>
<?xml version="1.0" encoding="ASCII"?><PRODUCT><ID>A002</ID>..</PRODUCT><SHOP-1><QUANTITY>nn</QUANITY><SHOP-1><QUANTITY>nn</QUANITY>
If you can assume that each xml document begins with <?xml version="1.0" ..., simply read the file line-by-line looking for a lines that match that pattern (or, read all the data and then do a search through the data).
Once you find a line, keep it, and append subsequent lines until the next xml document is found or you hit EOF. lather, rinse, repeat.
You now have one xml document in a string. You can then parse the string using the normal XML parsing tools, or you write it to a file.
This will work fine in most cases, but of course it could fall down if one of your embedded xml documents contains data that exactly matches the same pattern as the beginning of a document. Most likely you don't have to worry about that, and if you do there are ways to avoid that with a little more cleverness.
The right solution really depends on your needs. If you're creating a general purpose must-work-at-all-times solution this might not be right for you. For real world, special purpose problems it's probably more than Good Enough, and often Good Enough is indeed Good Enough.
You should see this python program by Michiel de Hoon
And if you want to parse multiple files, then a rule to detect that we are in other xml must be developed, for example,at first you read <stocks> .... and at the end you must reead </stocks> when you find that then if there is something else,well, continue reading and do the same parser until reach eof.
# Copyright 2008 by Michiel de Hoon. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Parser for XML results returned by NCBI's Entrez Utilities. This
parser is used by the read() function in Bio.Entrez, and is not intended
be used directly.
"""
# The question is how to represent an XML file as Python objects. Some
# XML files returned by NCBI look like lists, others look like dictionaries,
# and others look like a mix of lists and dictionaries.
#
# My approach is to classify each possible element in the XML as a plain
# string, an integer, a list, a dictionary, or a structure. The latter is a
# dictionary where the same key can occur multiple times; in Python, it is
# represented as a dictionary where that key occurs once, pointing to a list
# of values found in the XML file.
#
# The parser then goes through the XML and creates the appropriate Python
# object for each element. The different levels encountered in the XML are
# preserved on the Python side. So a subelement of a subelement of an element
# is a value in a dictionary that is stored in a list which is a value in
# some other dictionary (or a value in a list which itself belongs to a list
# which is a value in a dictionary, and so on). Attributes encountered in
# the XML are stored as a dictionary in a member .attributes of each element,
# and the tag name is saved in a member .tag.
#
# To decide which kind of Python object corresponds to each element in the
# XML, the parser analyzes the DTD referred at the top of (almost) every
# XML file returned by the Entrez Utilities. This is preferred over a hand-
# written solution, since the number of DTDs is rather large and their
# contents may change over time. About half the code in this parser deals
# wih parsing the DTD, and the other half with the XML itself.
import os.path
import urlparse
import urllib
import warnings
from xml.parsers import expat
# The following four classes are used to add a member .attributes to integers,
# strings, lists, and dictionaries, respectively.
class IntegerElement(int):
def __repr__(self):
text = int.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "IntegerElement(%s, attributes=%s)" % (text, repr(attributes))
class StringElement(str):
def __repr__(self):
text = str.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "StringElement(%s, attributes=%s)" % (text, repr(attributes))
class UnicodeElement(unicode):
def __repr__(self):
text = unicode.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "UnicodeElement(%s, attributes=%s)" % (text, repr(attributes))
class ListElement(list):
def __repr__(self):
text = list.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "ListElement(%s, attributes=%s)" % (text, repr(attributes))
class DictionaryElement(dict):
def __repr__(self):
text = dict.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "DictElement(%s, attributes=%s)" % (text, repr(attributes))
# A StructureElement is like a dictionary, but some of its keys can have
# multiple values associated with it. These values are stored in a list
# under each key.
class StructureElement(dict):
def __init__(self, keys):
dict.__init__(self)
for key in keys:
dict.__setitem__(self, key, [])
self.listkeys = keys
def __setitem__(self, key, value):
if key in self.listkeys:
self[key].append(value)
else:
dict.__setitem__(self, key, value)
def __repr__(self):
text = dict.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "DictElement(%s, attributes=%s)" % (text, repr(attributes))
class NotXMLError(ValueError):
def __init__(self, message):
self.msg = message
def __str__(self):
return "Failed to parse the XML data (%s). Please make sure that the input data are in XML format." % self.msg
class CorruptedXMLError(ValueError):
def __init__(self, message):
self.msg = message
def __str__(self):
return "Failed to parse the XML data (%s). Please make sure that the input data are not corrupted." % self.msg
class ValidationError(ValueError):
"""Validating parsers raise this error if the parser finds a tag in the XML that is not defined in the DTD. Non-validating parsers do not raise this error. The Bio.Entrez.read and Bio.Entrez.parse functions use validating parsers by default (see those functions for more information)"""
def __init__(self, name):
self.name = name
def __str__(self):
return "Failed to find tag '%s' in the DTD. To skip all tags that are not represented in the DTD, please call Bio.Entrez.read or Bio.Entrez.parse with validate=False." % self.name
class DataHandler:
home = os.path.expanduser('~')
local_dtd_dir = os.path.join(home, '.biopython', 'Bio', 'Entrez', 'DTDs')
del home
from Bio import Entrez
global_dtd_dir = os.path.join(str(Entrez.__path__[0]), "DTDs")
del Entrez
def __init__(self, validate):
self.stack = []
self.errors = []
self.integers = []
self.strings = []
self.lists = []
self.dictionaries = []
self.structures = {}
self.items = []
self.dtd_urls = []
self.validating = validate
self.parser = expat.ParserCreate(namespace_separator=" ")
self.parser.SetParamEntityParsing(expat.XML_PARAM_ENTITY_PARSING_ALWAYS)
self.parser.XmlDeclHandler = self.xmlDeclHandler
def read(self, handle):
"""Set up the parser and let it parse the XML results"""
try:
self.parser.ParseFile(handle)
except expat.ExpatError, e:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, so we can be sure that
# we are parsing XML data. Most likely, the XML file is
# corrupted.
raise CorruptedXMLError(e)
else:
# We have not seen the initial <!xml declaration, so probably
# the input data is not in XML format.
raise NotXMLError(e)
try:
return self.object
except AttributeError:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, and expat didn't notice
# any errors, so self.object should be defined. If not, this is
# a bug.
raise RuntimeError("Failed to parse the XML file correctly, possibly due to a bug in Bio.Entrez. Please contact the Biopython developers at biopython-dev#biopython.org for assistance.")
else:
# We did not see the initial <!xml declaration, so probably
# the input data is not in XML format.
raise NotXMLError("XML declaration not found")
def parse(self, handle):
BLOCK = 1024
while True:
#Read in another block of the file...
text = handle.read(BLOCK)
if not text:
# We have reached the end of the XML file
if self.stack:
# No more XML data, but there is still some unfinished
# business
raise CorruptedXMLError
try:
for record in self.object:
yield record
except AttributeError:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, and expat
# didn't notice any errors, so self.object should be
# defined. If not, this is a bug.
raise RuntimeError("Failed to parse the XML file correctly, possibly due to a bug in Bio.Entrez. Please contact the Biopython developers at biopython-dev#biopython.org for assistance.")
else:
# We did not see the initial <!xml declaration, so
# probably the input data is not in XML format.
raise NotXMLError("XML declaration not found")
self.parser.Parse("", True)
self.parser = None
return
try:
self.parser.Parse(text, False)
except expat.ExpatError, e:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, so we can be sure
# that we are parsing XML data. Most likely, the XML file
# is corrupted.
raise CorruptedXMLError(e)
else:
# We have not seen the initial <!xml declaration, so
# probably the input data is not in XML format.
raise NotXMLError(e)
if not self.stack:
# Haven't read enough from the XML file yet
continue
records = self.stack[0]
if not isinstance(records, list):
raise ValueError("The XML file does not represent a list. Please use Entrez.read instead of Entrez.parse")
while len(records) > 1: # Then the top record is finished
record = records.pop(0)
yield record
def xmlDeclHandler(self, version, encoding, standalone):
# XML declaration found; set the handlers
self.parser.StartElementHandler = self.startElementHandler
self.parser.EndElementHandler = self.endElementHandler
self.parser.CharacterDataHandler = self.characterDataHandler
self.parser.ExternalEntityRefHandler = self.externalEntityRefHandler
self.parser.StartNamespaceDeclHandler = self.startNamespaceDeclHandler
def startNamespaceDeclHandler(self, prefix, un):
raise NotImplementedError("The Bio.Entrez parser cannot handle XML data that make use of XML namespaces")
def startElementHandler(self, name, attrs):
self.content = ""
if name in self.lists:
object = ListElement()
elif name in self.dictionaries:
object = DictionaryElement()
elif name in self.structures:
object = StructureElement(self.structures[name])
elif name in self.items: # Only appears in ESummary
name = str(attrs["Name"]) # convert from Unicode
del attrs["Name"]
itemtype = str(attrs["Type"]) # convert from Unicode
del attrs["Type"]
if itemtype=="Structure":
object = DictionaryElement()
elif name in ("ArticleIds", "History"):
object = StructureElement(["pubmed", "medline"])
elif itemtype=="List":
object = ListElement()
else:
object = StringElement()
object.itemname = name
object.itemtype = itemtype
elif name in self.strings + self.errors + self.integers:
self.attributes = attrs
return
else:
# Element not found in DTD
if self.validating:
raise ValidationError(name)
else:
# this will not be stored in the record
object = ""
if object!="":
object.tag = name
if attrs:
object.attributes = dict(attrs)
if len(self.stack)!=0:
current = self.stack[-1]
try:
current.append(object)
except AttributeError:
current[name] = object
self.stack.append(object)
def endElementHandler(self, name):
value = self.content
if name in self.errors:
if value=="":
return
else:
raise RuntimeError(value)
elif name in self.integers:
value = IntegerElement(value)
elif name in self.strings:
# Convert Unicode strings to plain strings if possible
try:
value = StringElement(value)
except UnicodeEncodeError:
value = UnicodeElement(value)
elif name in self.items:
self.object = self.stack.pop()
if self.object.itemtype in ("List", "Structure"):
return
elif self.object.itemtype=="Integer" and value:
value = IntegerElement(value)
else:
# Convert Unicode strings to plain strings if possible
try:
value = StringElement(value)
except UnicodeEncodeError:
value = UnicodeElement(value)
name = self.object.itemname
else:
self.object = self.stack.pop()
return
value.tag = name
if self.attributes:
value.attributes = dict(self.attributes)
del self.attributes
current = self.stack[-1]
if current!="":
try:
current.append(value)
except AttributeError:
current[name] = value
def characterDataHandler(self, content):
self.content += content
def elementDecl(self, name, model):
"""This callback function is called for each element declaration:
<!ELEMENT name (...)>
encountered in a DTD. The purpose of this function is to determine
whether this element should be regarded as a string, integer, list
dictionary, structure, or error."""
if name.upper()=="ERROR":
self.errors.append(name)
return
if name=='Item' and model==(expat.model.XML_CTYPE_MIXED,
expat.model.XML_CQUANT_REP,
None, ((expat.model.XML_CTYPE_NAME,
expat.model.XML_CQUANT_NONE,
'Item',
()
),
)
):
# Special case. As far as I can tell, this only occurs in the
# eSummary DTD.
self.items.append(name)
return
# First, remove ignorable parentheses around declarations
while (model[0] in (expat.model.XML_CTYPE_SEQ,
expat.model.XML_CTYPE_CHOICE)
and model[1] in (expat.model.XML_CQUANT_NONE,
expat.model.XML_CQUANT_OPT)
and len(model[3])==1):
model = model[3][0]
# PCDATA declarations correspond to strings
if model[0] in (expat.model.XML_CTYPE_MIXED,
expat.model.XML_CTYPE_EMPTY):
self.strings.append(name)
return
# List-type elements
if (model[0] in (expat.model.XML_CTYPE_CHOICE,
expat.model.XML_CTYPE_SEQ) and
model[1] in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP)):
self.lists.append(name)
return
# This is the tricky case. Check which keys can occur multiple
# times. If only one key is possible, and it can occur multiple
# times, then this is a list. If more than one key is possible,
# but none of them can occur multiple times, then this is a
# dictionary. Otherwise, this is a structure.
# In 'single' and 'multiple', we keep track which keys can occur
# only once, and which can occur multiple times.
single = []
multiple = []
# The 'count' function is called recursively to make sure all the
# children in this model are counted. Error keys are ignored;
# they raise an exception in Python.
def count(model):
quantifier, name, children = model[1:]
if name==None:
if quantifier in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP):
for child in children:
multiple.append(child[2])
else:
for child in children:
count(child)
elif name.upper()!="ERROR":
if quantifier in (expat.model.XML_CQUANT_NONE,
expat.model.XML_CQUANT_OPT):
single.append(name)
elif quantifier in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP):
multiple.append(name)
count(model)
if len(single)==0 and len(multiple)==1:
self.lists.append(name)
elif len(multiple)==0:
self.dictionaries.append(name)
else:
self.structures.update({name: multiple})
def open_dtd_file(self, filename):
path = os.path.join(DataHandler.local_dtd_dir, filename)
try:
handle = open(path, "rb")
except IOError:
pass
else:
return handle
path = os.path.join(DataHandler.global_dtd_dir, filename)
try:
handle = open(path, "rb")
except IOError:
pass
else:
return handle
return None
def externalEntityRefHandler(self, context, base, systemId, publicId):
"""The purpose of this function is to load the DTD locally, instead
of downloading it from the URL specified in the XML. Using the local
DTD results in much faster parsing. If the DTD is not found locally,
we try to download it. If new DTDs become available from NCBI,
putting them in Bio/Entrez/DTDs will allow the parser to see them."""
urlinfo = urlparse.urlparse(systemId)
#Following attribute requires Python 2.5+
#if urlinfo.scheme=='http':
if urlinfo[0]=='http':
# Then this is an absolute path to the DTD.
url = systemId
elif urlinfo[0]=='':
# Then this is a relative path to the DTD.
# Look at the parent URL to find the full path.
url = self.dtd_urls[-1]
source = os.path.dirname(url)
url = os.path.join(source, systemId)
self.dtd_urls.append(url)
# First, try to load the local version of the DTD file
location, filename = os.path.split(systemId)
handle = self.open_dtd_file(filename)
if not handle:
# DTD is not available as a local file. Try accessing it through
# the internet instead.
message = """\
Unable to load DTD file %s.
Bio.Entrez uses NCBI's DTD files to parse XML files returned by NCBI Entrez.
Though most of NCBI's DTD files are included in the Biopython distribution,
sometimes you may find that a particular DTD file is missing. While we can
access the DTD file through the internet, the parser is much faster if the
required DTD files are available locally.
For this purpose, please download %s from
%s
and save it either in directory
%s
or in directory
%s
in order for Bio.Entrez to find it.
Alternatively, you can save %s in the directory
Bio/Entrez/DTDs in the Biopython distribution, and reinstall Biopython.
Please also inform the Biopython developers about this missing DTD, by
reporting a bug on http://bugzilla.open-bio.org/ or sign up to our mailing
list and emailing us, so that we can include it with the next release of
Biopython.
Proceeding to access the DTD file through the internet...
""" % (filename, filename, url, self.global_dtd_dir, self.local_dtd_dir, filename)
warnings.warn(message)
try:
handle = urllib.urlopen(url)
except IOError:
raise RuntimeException("Failed to access %s at %s" % (filename, url))
parser = self.parser.ExternalEntityParserCreate(context)
parser.ElementDeclHandler = self.elementDecl
parser.ParseFile(handle)
handle.close()
self.dtd_urls.pop()
return 1
So you have a file containing multiple XML documents one after the other? Here is an example which strips out the <?xml ?> PIs and wraps the data in a root tag to parse the whole thing as a single XML document:
import re
import lxml.etree
re_strip_pi = re.compile('<\?xml [^?>]+\?>', re.M)
data = '<root>' + open('stocks.xml', 'rb').read() + '</root>'
match = re_strip_pi.search(data)
data = re_strip_pi.sub('', data)
tree = lxml.etree.fromstring(match.group() + data)
for prod in tree.xpath('//PRODUCT'):
print prod
You can't have multiple XML documents in one XML file. Split the documents - composed in whatever way - into single XML files and parse them one-by-one.