diff options
| -rw-r--r-- | mammoth/conversion.py | 15 | ||||
| -rw-r--r-- | mammoth/document_matchers.py | 4 | ||||
| -rw-r--r-- | mammoth/style_reader/document_matcher_reader.py | 6 | ||||
| -rw-r--r-- | tests/conversion_tests.py | 11 | ||||
| -rw-r--r-- | tests/mammoth_tests.py | 7 | ||||
| -rw-r--r-- | tests/style_reader_tests.py | 7 |
6 files changed, 46 insertions, 4 deletions
diff --git a/mammoth/conversion.py b/mammoth/conversion.py index c4631e1..71edaf4 100644 --- a/mammoth/conversion.py +++ b/mammoth/conversion.py @@ -100,7 +100,7 @@ class DocumentConverter(object): if run.is_underline: self._convert_underline(run_generator) if run.is_strikethrough: - run_generator.start("s") + self._convert_strikethrough(run_generator) self._convert_elements_to_html(run.children, run_generator) run_generator.end_all() html_generator.append(run_generator) @@ -111,6 +111,15 @@ class DocumentConverter(object): if style is not None: append_html_path(run_generator, style.html_path) + + def _convert_strikethrough(self, run_generator): + style = self._find_style(None, "strikethrough") + if style is None: + run_generator.start("s") + else: + append_html_path(run_generator, style.html_path) + + def _convert_text(self, text, html_generator): html_generator.text(text.value) @@ -238,8 +247,8 @@ class DocumentConverter(object): def _document_matcher_matches(matcher, element, element_type): - if matcher.element_type == "underline": - return element_type == "underline" + if matcher.element_type in ["underline", "strikethrough"]: + return matcher.element_type == element_type else: return ( matcher.element_type == element_type and ( diff --git a/mammoth/document_matchers.py b/mammoth/document_matchers.py index 07d5be2..9f05a8e 100644 --- a/mammoth/document_matchers.py +++ b/mammoth/document_matchers.py @@ -19,3 +19,7 @@ RunMatcher.element_type = "run" class underline(object): element_type = "underline" + + +class strikethrough(object): + element_type = "strikethrough" diff --git a/mammoth/style_reader/document_matcher_reader.py b/mammoth/style_reader/document_matcher_reader.py index 56c4626..04a26c0 100644 --- a/mammoth/style_reader/document_matcher_reader.py +++ b/mammoth/style_reader/document_matcher_reader.py @@ -16,6 +16,8 @@ def read_document_matcher_node(root_node): return _read_run_node(element_node) elif element_node.expr_name == "underline": return document_matchers.underline + elif element_node.expr_name == "strikethrough": + return document_matchers.strikethrough def _read_paragraph_node(paragraph_node): @@ -55,10 +57,12 @@ def _read_list_node(list_node): return None grammar_text = r""" -document_matcher = paragraph / run / underline +document_matcher = paragraph / run / underline / strikethrough underline = "u" +strikethrough = "strike" + paragraph = "p" style_id? style_name_specifier? list? run = "r" style_id? style_name_specifier? diff --git a/tests/conversion_tests.py b/tests/conversion_tests.py index 1563131..23e61d4 100644 --- a/tests/conversion_tests.py +++ b/tests/conversion_tests.py @@ -211,6 +211,17 @@ def strikethrough_runs_are_wrapped_in_s_elements_by_default(): @istest +def strikethrough_runs_can_be_configured_with_style_mapping(): + result = convert_document_element_to_html( + documents.run(children=[documents.text("Hello")], is_strikethrough=True), + style_map=[ + style_reader.read_style("strike => del") + ] + ) + assert_equal("<del>Hello</del>", result.value) + + +@istest def superscript_runs_are_wrapped_in_sup_tags(): result = convert_document_element_to_html( documents.run( diff --git a/tests/mammoth_tests.py b/tests/mammoth_tests.py index 84cb6ea..9f37db0 100644 --- a/tests/mammoth_tests.py +++ b/tests/mammoth_tests.py @@ -138,6 +138,13 @@ def strikethrough_is_converted_to_s_element_by_default(): @istest +def strikethrough_conversion_can_be_configured_with_style_mapping(): + with open(test_path("strikethrough.docx"), "rb") as fileobj: + result = mammoth.convert_to_html(fileobj=fileobj, style_map="strike => del") + assert_equal("<p><del>Today's Special: Salmon</del> Sold out</p>", result.value) + + +@istest def transform_document_is_applied_to_document_before_conversion(): def transform_document(document): document.children[0].style_id = "Heading1" diff --git a/tests/style_reader_tests.py b/tests/style_reader_tests.py index 501629a..52d66fd 100644 --- a/tests/style_reader_tests.py +++ b/tests/style_reader_tests.py @@ -141,6 +141,13 @@ class ReadDocumentMatcherTests(object): read_document_matcher("u") ) + @istest + def reads_strikethrough(self): + assert_equal( + document_matchers.strikethrough, + read_document_matcher("strike") + ) + @istest def document_matcher_is_mapped_to_html_path_using_fat_arrow(): |