diff options
| -rw-r--r-- | mammoth/docx/__init__.py | 96 | ||||
| -rw-r--r-- | mammoth/docx/comments_xml.py | 4 | ||||
| -rw-r--r-- | mammoth/docx/notes_xml.py | 8 | ||||
| -rw-r--r-- | tests/docx/comments_xml_tests.py | 18 | ||||
| -rw-r--r-- | tests/docx/notes_xml_tests.py | 10 |
5 files changed, 81 insertions, 55 deletions
diff --git a/mammoth/docx/__init__.py b/mammoth/docx/__init__.py index b155cff..9d0cdc2 100644 --- a/mammoth/docx/__init__.py +++ b/mammoth/docx/__init__.py @@ -1,3 +1,4 @@ +from functools import partial import os from .. import results, lists @@ -6,8 +7,8 @@ from .content_types_xml import empty_content_types, read_content_types_xml_eleme from .relationships_xml import read_relationships_xml_element, Relationships from .numbering_xml import read_numbering_xml_element, Numbering from .styles_xml import read_styles_xml_element, Styles -from .notes_xml import create_footnotes_reader, create_endnotes_reader -from .comments_xml import create_comments_reader +from .notes_xml import read_endnotes_xml_element, read_footnotes_xml_element +from .comments_xml import read_comments_xml_element from .files import Files from . import body_xml, office_xml from ..zips import open_zip @@ -18,38 +19,40 @@ _empty_result = results.success([]) def read(fileobj): zip_file = open_zip(fileobj, "r") - body_readers = _body_readers(getattr(fileobj, "name", None), zip_file) + read_part_with_body = _part_with_body_reader(getattr(fileobj, "name", None), zip_file) return results.combine([ - _read_notes(zip_file, body_readers), - _read_comments(zip_file, body_readers), + _read_notes(zip_file, read_part_with_body), + _read_comments(zip_file, read_part_with_body), ]).bind(lambda referents: - _read_document(zip_file, body_readers, notes=referents[0], comments=referents[1]) + _read_document(zip_file, read_part_with_body, notes=referents[0], comments=referents[1]) ) -def _read_notes(zip_file, body_readers): - read_footnotes_xml = create_footnotes_reader(body_readers("footnotes")) - footnotes = _try_read_entry_or_default( - zip_file, "word/footnotes.xml", read_footnotes_xml, default=_empty_result) - - read_endnotes_xml = create_endnotes_reader(body_readers("endnotes")) - endnotes = _try_read_entry_or_default( - zip_file, "word/endnotes.xml", read_endnotes_xml, default=_empty_result) +def _read_notes(zip_file, read_part_with_body): + footnotes = read_part_with_body( + "word/footnotes.xml", + lambda root, body_reader: read_footnotes_xml_element(root, body_reader=body_reader), + default=_empty_result, + ) + endnotes = read_part_with_body( + "word/endnotes.xml", + lambda root, body_reader: read_endnotes_xml_element(root, body_reader=body_reader), + default=_empty_result, + ) return results.combine([footnotes, endnotes]).map(lists.flatten) -def _read_comments(zip_file, body_readers): - return _try_read_entry_or_default( - zip_file, +def _read_comments(zip_file, read_part_with_body): + return read_part_with_body( "word/comments.xml", - create_comments_reader(body_readers("comments")), + lambda root, body_reader: read_comments_xml_element(root, body_reader=body_reader), default=_empty_result, ) -def _read_document(zip_file, body_readers, notes, comments): +def _read_document(zip_file, read_part_with_body, notes, comments): package_relationships = _try_read_entry_or_default( zip_file, "_rels/.rels", @@ -59,14 +62,14 @@ def _read_document(zip_file, body_readers, notes, comments): document_filename = _find_document_filename(zip_file, package_relationships) - with zip_file.open(document_filename) as document_fileobj: - document_xml = office_xml.read(document_fileobj) - return read_document_xml_element( - document_xml, - body_reader=body_readers("document"), + return read_part_with_body( + document_filename, + partial( + read_document_xml_element, notes=notes, comments=comments, - ) + ), + ) def _find_document_filename(zip_file, relationships): @@ -82,7 +85,7 @@ def _find_document_filename(zip_file, relationships): return valid_targets[0] -def _body_readers(document_path, zip_file): +def _part_with_body_reader(document_path, zip_file): content_types = _try_read_entry_or_default( zip_file, "[Content_Types].xml", @@ -100,13 +103,10 @@ def _body_readers(document_path, zip_file): Styles.EMPTY, ) - def for_name(name): - relationships_path = "word/_rels/{0}.xml.rels".format(name) - relationships = _try_read_entry_or_default( - zip_file, relationships_path, read_relationships_xml_element, - default=Relationships.EMPTY) + def read_part(name, reader, default=_undefined): + relationships = _read_relationships(zip_file, _find_relationships_path_for(name)) - return body_xml.reader( + body_reader = body_xml.reader( numbering=numbering, content_types=content_types, relationships=relationships, @@ -114,13 +114,39 @@ def _body_readers(document_path, zip_file): docx_file=zip_file, files=Files(None if document_path is None else os.path.dirname(document_path)), ) + + if default is _undefined: + return _read_entry(zip_file, name, partial(reader, body_reader=body_reader)) + else: + return _try_read_entry_or_default(zip_file, name, partial(reader, body_reader=body_reader), default=default) - return for_name + return read_part + +def _find_relationships_path_for(name): + parts = name.split("/") + return "/".join(parts[:-1] + ["_rels/" + parts[-1] + ".rels"]) + + +def _read_relationships(zip_file, name): + return _try_read_entry_or_default( + zip_file, + name, + read_relationships_xml_element, + default=Relationships.EMPTY, + ) + def _try_read_entry_or_default(zip_file, name, reader, default): if zip_file.exists(name): - with zip_file.open(name) as fileobj: - return reader(office_xml.read(fileobj)) + return _read_entry(zip_file, name, reader) else: return default + + +def _read_entry(zip_file, name, reader): + with zip_file.open(name) as fileobj: + return reader(office_xml.read(fileobj)) + + +_undefined = object() diff --git a/mammoth/docx/comments_xml.py b/mammoth/docx/comments_xml.py index 6d35c12..387432f 100644 --- a/mammoth/docx/comments_xml.py +++ b/mammoth/docx/comments_xml.py @@ -3,7 +3,7 @@ from .. import documents from .. import results -def create_comments_reader(body_reader): +def read_comments_xml_element(element, body_reader): def read_comments_xml_element(element): comment_elements = element.find_children("w:comment") return results.combine(lists.map(_read_comment_element, comment_elements)) @@ -21,4 +21,4 @@ def create_comments_reader(body_reader): author_initials=read_optional_attribute("w:initials"), )) - return read_comments_xml_element + return read_comments_xml_element(element) diff --git a/mammoth/docx/notes_xml.py b/mammoth/docx/notes_xml.py index f1072f9..5e4ea4e 100644 --- a/mammoth/docx/notes_xml.py +++ b/mammoth/docx/notes_xml.py @@ -5,7 +5,7 @@ from .. import documents from .. import results -def create_reader(note_type, body_reader): +def _read_notes(note_type, element, body_reader): def read_notes_xml_element(element): note_elements = lists.filter( _is_note_element, @@ -26,7 +26,7 @@ def create_reader(note_type, body_reader): body=body )) - return read_notes_xml_element + return read_notes_xml_element(element) -create_footnotes_reader = functools.partial(create_reader, "footnote") -create_endnotes_reader = functools.partial(create_reader, "endnote") +read_footnotes_xml_element = functools.partial(_read_notes, "footnote") +read_endnotes_xml_element = functools.partial(_read_notes, "endnote") diff --git a/tests/docx/comments_xml_tests.py b/tests/docx/comments_xml_tests.py index eb52c21..1d5dd8d 100644 --- a/tests/docx/comments_xml_tests.py +++ b/tests/docx/comments_xml_tests.py @@ -2,16 +2,16 @@ from nose.tools import istest, assert_equal from mammoth import documents from mammoth.docx.xmlparser import element as xml_element -from mammoth.docx.comments_xml import create_comments_reader +from mammoth.docx.comments_xml import read_comments_xml_element from mammoth.docx import body_xml @istest def id_and_body_of_comment_is_read(): body = [xml_element("w:p")] - comments = create_comments_reader(body_xml.reader())(xml_element("w:comments", {}, [ + comments = read_comments_xml_element(xml_element("w:comments", {}, [ xml_element("w:comment", {"w:id": "1"}, body), - ])) + ]), body_reader=body_xml.reader()) assert_equal(1, len(comments.value)) assert_equal(comments.value[0].body, [documents.paragraph(children=[])]) assert_equal("1", comments.value[0].comment_id) @@ -19,9 +19,9 @@ def id_and_body_of_comment_is_read(): @istest def when_optional_attributes_of_comment_are_missing_then_they_are_read_as_none(): - comments = create_comments_reader(body_xml.reader())(xml_element("w:comments", {}, [ + comments = read_comments_xml_element(xml_element("w:comments", {}, [ xml_element("w:comment", {"w:id": "1"}, []), - ])) + ]), body_reader=body_xml.reader()) comment, = comments.value assert_equal(None, comment.author_name) assert_equal(None, comment.author_initials) @@ -29,9 +29,9 @@ def when_optional_attributes_of_comment_are_missing_then_they_are_read_as_none() @istest def when_optional_attributes_of_comment_are_blank_then_they_are_read_as_none(): - comments = create_comments_reader(body_xml.reader())(xml_element("w:comments", {}, [ + comments = read_comments_xml_element(xml_element("w:comments", {}, [ xml_element("w:comment", {"w:id": "1", "w:author": " ", "w:initials": " "}, []), - ])) + ]), body_reader=body_xml.reader()) comment, = comments.value assert_equal(None, comment.author_name) assert_equal(None, comment.author_initials) @@ -39,9 +39,9 @@ def when_optional_attributes_of_comment_are_blank_then_they_are_read_as_none(): @istest def when_optional_attributes_of_comment_are_not_blank_then_they_are_read(): - comments = create_comments_reader(body_xml.reader())(xml_element("w:comments", {}, [ + comments = read_comments_xml_element(xml_element("w:comments", {}, [ xml_element("w:comment", {"w:id": "1", "w:author": "The Piemaker", "w:initials": "TP"}, []), - ])) + ]), body_reader=body_xml.reader()) comment, = comments.value assert_equal("The Piemaker", comment.author_name) assert_equal("TP", comment.author_initials) diff --git a/tests/docx/notes_xml_tests.py b/tests/docx/notes_xml_tests.py index b912991..56a7681 100644 --- a/tests/docx/notes_xml_tests.py +++ b/tests/docx/notes_xml_tests.py @@ -2,16 +2,16 @@ from nose.tools import istest, assert_equal from mammoth import documents from mammoth.docx.xmlparser import element as xml_element -from mammoth.docx.notes_xml import create_footnotes_reader +from mammoth.docx.notes_xml import read_footnotes_xml_element from mammoth.docx import body_xml @istest def id_and_body_of_footnote_are_read(): footnote_body = [xml_element("w:p")] - footnotes = create_footnotes_reader(body_xml.reader())(xml_element("w:footnotes", {}, [ + footnotes = read_footnotes_xml_element(xml_element("w:footnotes", {}, [ xml_element("w:footnote", {"w:id": "1"}, footnote_body), - ])) + ]), body_reader=body_xml.reader()) assert_equal(1, len(footnotes.value)) assert isinstance(footnotes.value[0].body[0], documents.Paragraph) assert_equal("1", footnotes.value[0].note_id) @@ -29,8 +29,8 @@ def separator_is_ignored(): def _assert_footnote_type_is_ignored(footnote_type): footnote_body = [xml_element("w:p")] - footnotes = create_footnotes_reader(None)(xml_element("w:footnotes", {}, [ + footnotes = read_footnotes_xml_element(xml_element("w:footnotes", {}, [ xml_element("w:footnote", {"w:id": "1", "w:type": footnote_type}, footnote_body), - ])) + ]), body_reader=None) assert_equal(0, len(footnotes.value)) |