lxml 5.2.0__cp310-cp310-win32.whl → 5.2.2__cp310-cp310-win32.whl

lxml/html/_diffcommand.py

@@ -1,86 +1,86 @@
-import optparse
-import sys
-import re
-import os
-from .diff import htmldiff
-
-description = """\
-"""
-
-parser = optparse.OptionParser(
-    usage="%prog [OPTIONS] FILE1 FILE2\n"
-    "%prog --annotate [OPTIONS] INFO1 FILE1 INFO2 FILE2 ...",
-    description=description,
-    )
-
-parser.add_option(
-    '-o', '--output',
-    metavar="FILE",
-    dest="output",
-    default="-",
-    help="File to write the difference to",
-    )
-
-parser.add_option(
-    '-a', '--annotation',
-    action="store_true",
-    dest="annotation",
-    help="Do an annotation")
-
-def main(args=None):
-    if args is None:
-        args = sys.argv[1:]
-    options, args = parser.parse_args(args)
-    if options.annotation:
-        return annotate(options, args)
-    if len(args) != 2:
-        print('Error: you must give two files')
-        parser.print_help()
-        sys.exit(1)
-    file1, file2 = args
-    input1 = read_file(file1)
-    input2 = read_file(file2)
-    body1 = split_body(input1)[1]
-    pre, body2, post = split_body(input2)
-    result = htmldiff(body1, body2)
-    result = pre + result + post
-    if options.output == '-':
-        if not result.endswith('\n'):
-            result += '\n'
-        sys.stdout.write(result)
-    else:
-        with open(options.output, 'wb') as f:
-            f.write(result)
-
-def read_file(filename):
-    if filename == '-':
-        c = sys.stdin.read()
-    elif not os.path.exists(filename):
-        raise OSError(
-            "Input file %s does not exist" % filename)
-    else:
-        with open(filename, 'rb') as f:
-            c = f.read()
-    return c
-
-body_start_re = re.compile(
-    r"<body.*?>", re.I|re.S)
-body_end_re = re.compile(
-    r"</body.*?>", re.I|re.S)
-    
-def split_body(html):
-    pre = post = ''
-    match = body_start_re.search(html)
-    if match:
-        pre = html[:match.end()]
-        html = html[match.end():]
-    match = body_end_re.search(html)
-    if match:
-        post = html[match.start():]
-        html = html[:match.start()]
-    return pre, html, post
-
-def annotate(options, args):
-    print("Not yet implemented")
-    sys.exit(1)
-    
+import optparse
+import sys
+import re
+import os
+from .diff import htmldiff
+
+description = """\
+"""
+
+parser = optparse.OptionParser(
+    usage="%prog [OPTIONS] FILE1 FILE2\n"
+    "%prog --annotate [OPTIONS] INFO1 FILE1 INFO2 FILE2 ...",
+    description=description,
+    )
+
+parser.add_option(
+    '-o', '--output',
+    metavar="FILE",
+    dest="output",
+    default="-",
+    help="File to write the difference to",
+    )
+
+parser.add_option(
+    '-a', '--annotation',
+    action="store_true",
+    dest="annotation",
+    help="Do an annotation")
+
+def main(args=None):
+    if args is None:
+        args = sys.argv[1:]
+    options, args = parser.parse_args(args)
+    if options.annotation:
+        return annotate(options, args)
+    if len(args) != 2:
+        print('Error: you must give two files')
+        parser.print_help()
+        sys.exit(1)
+    file1, file2 = args
+    input1 = read_file(file1)
+    input2 = read_file(file2)
+    body1 = split_body(input1)[1]
+    pre, body2, post = split_body(input2)
+    result = htmldiff(body1, body2)
+    result = pre + result + post
+    if options.output == '-':
+        if not result.endswith('\n'):
+            result += '\n'
+        sys.stdout.write(result)
+    else:
+        with open(options.output, 'wb') as f:
+            f.write(result)
+
+def read_file(filename):
+    if filename == '-':
+        c = sys.stdin.read()
+    elif not os.path.exists(filename):
+        raise OSError(
+            "Input file %s does not exist" % filename)
+    else:
+        with open(filename, 'rb') as f:
+            c = f.read()
+    return c
+
+body_start_re = re.compile(
+    r"<body.*?>", re.I|re.S)
+body_end_re = re.compile(
+    r"</body.*?>", re.I|re.S)
+    
+def split_body(html):
+    pre = post = ''
+    match = body_start_re.search(html)
+    if match:
+        pre = html[:match.end()]
+        html = html[match.end():]
+    match = body_end_re.search(html)
+    if match:
+        post = html[match.start():]
+        html = html[:match.start()]
+    return pre, html, post
+
+def annotate(options, args):
+    print("Not yet implemented")
+    sys.exit(1)
+    

lxml/html/_html5builder.py

@@ -1,100 +1,100 @@
-"""
-Legacy module - don't use in new code!
-
-html5lib now has its own proper implementation.
-
-This module implements a tree builder for html5lib that generates lxml
-html element trees.  This module uses camelCase as it follows the
-html5lib style guide.
-"""
-
-from html5lib.treebuilders import _base, etree as etree_builders
-from lxml import html, etree
-
-
-class DocumentType:
-
-    def __init__(self, name, publicId, systemId):
-        self.name = name
-        self.publicId = publicId
-        self.systemId = systemId
-
-class Document:
-
-    def __init__(self):
-        self._elementTree = None
-        self.childNodes = []
-
-    def appendChild(self, element):
-        self._elementTree.getroot().addnext(element._element)
-
-
-class TreeBuilder(_base.TreeBuilder):
-    documentClass = Document
-    doctypeClass = DocumentType
-    elementClass = None
-    commentClass = None
-    fragmentClass = Document
-
-    def __init__(self, *args, **kwargs):
-        html_builder = etree_builders.getETreeModule(html, fullTree=False)
-        etree_builder = etree_builders.getETreeModule(etree, fullTree=False)
-        self.elementClass = html_builder.Element
-        self.commentClass = etree_builder.Comment
-        _base.TreeBuilder.__init__(self, *args, **kwargs)
-
-    def reset(self):
-        _base.TreeBuilder.reset(self)
-        self.rootInserted = False
-        self.initialComments = []
-        self.doctype = None
-
-    def getDocument(self):
-        return self.document._elementTree
-
-    def getFragment(self):
-        fragment = []
-        element = self.openElements[0]._element
-        if element.text:
-            fragment.append(element.text)
-        fragment.extend(element.getchildren())
-        if element.tail:
-            fragment.append(element.tail)
-        return fragment
-
-    def insertDoctype(self, name, publicId, systemId):
-        doctype = self.doctypeClass(name, publicId, systemId)
-        self.doctype = doctype
-
-    def insertComment(self, data, parent=None):
-        if not self.rootInserted:
-            self.initialComments.append(data)
-        else:
-            _base.TreeBuilder.insertComment(self, data, parent)
-
-    def insertRoot(self, name):
-        buf = []
-        if self.doctype and self.doctype.name:
-            buf.append('<!DOCTYPE %s' % self.doctype.name)
-            if self.doctype.publicId is not None or self.doctype.systemId is not None:
-                buf.append(' PUBLIC "%s" "%s"' % (self.doctype.publicId,
-                                                  self.doctype.systemId))
-            buf.append('>')
-        buf.append('<html></html>')
-        root = html.fromstring(''.join(buf))
-
-        # Append the initial comments:
-        for comment in self.initialComments:
-            root.addprevious(etree.Comment(comment))
-
-        # Create the root document and add the ElementTree to it
-        self.document = self.documentClass()
-        self.document._elementTree = root.getroottree()
-
-        # Add the root element to the internal child/open data structures
-        root_element = self.elementClass(name)
-        root_element._element = root
-        self.document.childNodes.append(root_element)
-        self.openElements.append(root_element)
-
-        self.rootInserted = True
+"""
+Legacy module - don't use in new code!
+
+html5lib now has its own proper implementation.
+
+This module implements a tree builder for html5lib that generates lxml
+html element trees.  This module uses camelCase as it follows the
+html5lib style guide.
+"""
+
+from html5lib.treebuilders import _base, etree as etree_builders
+from lxml import html, etree
+
+
+class DocumentType:
+
+    def __init__(self, name, publicId, systemId):
+        self.name = name
+        self.publicId = publicId
+        self.systemId = systemId
+
+class Document:
+
+    def __init__(self):
+        self._elementTree = None
+        self.childNodes = []
+
+    def appendChild(self, element):
+        self._elementTree.getroot().addnext(element._element)
+
+
+class TreeBuilder(_base.TreeBuilder):
+    documentClass = Document
+    doctypeClass = DocumentType
+    elementClass = None
+    commentClass = None
+    fragmentClass = Document
+
+    def __init__(self, *args, **kwargs):
+        html_builder = etree_builders.getETreeModule(html, fullTree=False)
+        etree_builder = etree_builders.getETreeModule(etree, fullTree=False)
+        self.elementClass = html_builder.Element
+        self.commentClass = etree_builder.Comment
+        _base.TreeBuilder.__init__(self, *args, **kwargs)
+
+    def reset(self):
+        _base.TreeBuilder.reset(self)
+        self.rootInserted = False
+        self.initialComments = []
+        self.doctype = None
+
+    def getDocument(self):
+        return self.document._elementTree
+
+    def getFragment(self):
+        fragment = []
+        element = self.openElements[0]._element
+        if element.text:
+            fragment.append(element.text)
+        fragment.extend(element.getchildren())
+        if element.tail:
+            fragment.append(element.tail)
+        return fragment
+
+    def insertDoctype(self, name, publicId, systemId):
+        doctype = self.doctypeClass(name, publicId, systemId)
+        self.doctype = doctype
+
+    def insertComment(self, data, parent=None):
+        if not self.rootInserted:
+            self.initialComments.append(data)
+        else:
+            _base.TreeBuilder.insertComment(self, data, parent)
+
+    def insertRoot(self, name):
+        buf = []
+        if self.doctype and self.doctype.name:
+            buf.append('<!DOCTYPE %s' % self.doctype.name)
+            if self.doctype.publicId is not None or self.doctype.systemId is not None:
+                buf.append(' PUBLIC "%s" "%s"' % (self.doctype.publicId,
+                                                  self.doctype.systemId))
+            buf.append('>')
+        buf.append('<html></html>')
+        root = html.fromstring(''.join(buf))
+
+        # Append the initial comments:
+        for comment in self.initialComments:
+            root.addprevious(etree.Comment(comment))
+
+        # Create the root document and add the ElementTree to it
+        self.document = self.documentClass()
+        self.document._elementTree = root.getroottree()
+
+        # Add the root element to the internal child/open data structures
+        root_element = self.elementClass(name)
+        root_element._element = root
+        self.document.childNodes.append(root_element)
+        self.openElements.append(root_element)
+
+        self.rootInserted = True

lxml/html/_setmixin.py

@@ -1,56 +1,56 @@
-try:
-    from collections.abc import MutableSet
-except ImportError:
-    from collections.abc import MutableSet
-
-
-class SetMixin(MutableSet):
-
-    """
-    Mix-in for sets.  You must define __iter__, add, remove
-    """
-
-    def __len__(self):
-        length = 0
-        for item in self:
-            length += 1
-        return length
-
-    def __contains__(self, item):
-        for has_item in self:
-            if item == has_item:
-                return True
-        return False
-
-    issubset = MutableSet.__le__
-    issuperset = MutableSet.__ge__
-
-    union = MutableSet.__or__
-    intersection = MutableSet.__and__
-    difference = MutableSet.__sub__
-    symmetric_difference = MutableSet.__xor__
-
-    def copy(self):
-        return set(self)
-
-    def update(self, other):
-        self |= other
-
-    def intersection_update(self, other):
-        self &= other
-
-    def difference_update(self, other):
-        self -= other
-
-    def symmetric_difference_update(self, other):
-        self ^= other
-
-    def discard(self, item):
-        try:
-            self.remove(item)
-        except KeyError:
-            pass
-
-    @classmethod
-    def _from_iterable(cls, it):
-        return set(it)
+try:
+    from collections.abc import MutableSet
+except ImportError:
+    from collections.abc import MutableSet
+
+
+class SetMixin(MutableSet):
+
+    """
+    Mix-in for sets.  You must define __iter__, add, remove
+    """
+
+    def __len__(self):
+        length = 0
+        for item in self:
+            length += 1
+        return length
+
+    def __contains__(self, item):
+        for has_item in self:
+            if item == has_item:
+                return True
+        return False
+
+    issubset = MutableSet.__le__
+    issuperset = MutableSet.__ge__
+
+    union = MutableSet.__or__
+    intersection = MutableSet.__and__
+    difference = MutableSet.__sub__
+    symmetric_difference = MutableSet.__xor__
+
+    def copy(self):
+        return set(self)
+
+    def update(self, other):
+        self |= other
+
+    def intersection_update(self, other):
+        self &= other
+
+    def difference_update(self, other):
+        self -= other
+
+    def symmetric_difference_update(self, other):
+        self ^= other
+
+    def discard(self, item):
+        try:
+            self.remove(item)
+        except KeyError:
+            pass
+
+    @classmethod
+    def _from_iterable(cls, it):
+        return set(it)