diff options
| -rw-r--r-- | mammoth/__init__.py | 36 | ||||
| -rw-r--r-- | mammoth/conversion.py | 8 | ||||
| -rw-r--r-- | mammoth/options.py | 36 | ||||
| -rw-r--r-- | tests/conversion_tests.py | 10 |
4 files changed, 48 insertions, 42 deletions
diff --git a/mammoth/__init__.py b/mammoth/__init__.py index 84849ce..90ab764 100644 --- a/mammoth/__init__.py +++ b/mammoth/__init__.py @@ -1,41 +1,11 @@ from .results import Result -from . import docx, conversion, style_reader, lists +from . import docx, conversion, options -def convert_to_html(fileobj, style_map=None, convert_image=None): - if style_map is None: - style_map = _default_style_map - else: - style_map = _read_style_map(style_map) - +def convert_to_html(fileobj, **kwargs): return docx.read(fileobj).bind(lambda document: conversion.convert_document_element_to_html( document, - styles=style_map, - convert_image=convert_image, + **options.read_options(kwargs) ) ) - - -def _read_style_map(style_text): - lines = filter(None, map(lambda line: line.strip(), style_text.split("\n"))) - return lists.map(style_reader.read_style, lines) - - - -_default_style_map = _read_style_map(""" -p.Heading1 => h1:fresh -p.Heading2 => h2:fresh -p.Heading3 => h3:fresh -p.Heading4 => h4:fresh -p:unordered-list(1) => ul > li:fresh -p:unordered-list(2) => ul|ol > li > ul > li:fresh -p:unordered-list(3) => ul|ol > li > ul|ol > li > ul > li:fresh -p:unordered-list(4) => ul|ol > li > ul|ol > li > ul|ol > li > ul > li:fresh -p:unordered-list(5) => ul|ol > li > ul|ol > li > ul|ol > li > ul|ol > li > ul > li:fresh -p:ordered-list(1) => ol > li:fresh -p:ordered-list(2) => ul|ol > li > ol > li:fresh -p:ordered-list(3) => ul|ol > li > ul|ol > li > ol > li:fresh -p:ordered-list(4) => ul|ol > li > ul|ol > li > ul|ol > li > ol > li:fresh -p:ordered-list(5) => ul|ol > li > ul|ol > li > ul|ol > li > ul|ol > li > ol > li:fresh -""") diff --git a/mammoth/conversion.py b/mammoth/conversion.py index 835cb6b..8123ebd 100644 --- a/mammoth/conversion.py +++ b/mammoth/conversion.py @@ -5,11 +5,11 @@ from . import documents, results, html_paths from .html_generation import HtmlGenerator, satisfy_html_path -def convert_document_element_to_html(element, styles=None, convert_image=None): - if styles is None: - styles = [] +def convert_document_element_to_html(element, style_map=None, convert_image=None): + if style_map is None: + style_map = [] html_generator = HtmlGenerator() - converter = DocumentConverter(styles, convert_image=convert_image) + converter = DocumentConverter(style_map, convert_image=convert_image) converter.convert_element_to_html(element, html_generator,) html_generator.end_all() return results.Result(html_generator.html_string(), converter.messages) diff --git a/mammoth/options.py b/mammoth/options.py new file mode 100644 index 0000000..4e4d5f1 --- /dev/null +++ b/mammoth/options.py @@ -0,0 +1,36 @@ +from . import style_reader, lists + + +def read_options(options): + if options.get("style_map") is None: + style_map = _default_style_map + else: + style_map = _read_style_map(style_map) + + options["style_map"] = style_map + return options + + +def _read_style_map(style_text): + lines = filter(None, map(lambda line: line.strip(), style_text.split("\n"))) + return lists.map(style_reader.read_style, lines) + + + +_default_style_map = _read_style_map(""" +p.Heading1 => h1:fresh +p.Heading2 => h2:fresh +p.Heading3 => h3:fresh +p.Heading4 => h4:fresh +p:unordered-list(1) => ul > li:fresh +p:unordered-list(2) => ul|ol > li > ul > li:fresh +p:unordered-list(3) => ul|ol > li > ul|ol > li > ul > li:fresh +p:unordered-list(4) => ul|ol > li > ul|ol > li > ul|ol > li > ul > li:fresh +p:unordered-list(5) => ul|ol > li > ul|ol > li > ul|ol > li > ul|ol > li > ul > li:fresh +p:ordered-list(1) => ol > li:fresh +p:ordered-list(2) => ul|ol > li > ol > li:fresh +p:ordered-list(3) => ul|ol > li > ul|ol > li > ol > li:fresh +p:ordered-list(4) => ul|ol > li > ul|ol > li > ul|ol > li > ol > li:fresh +p:ordered-list(5) => ul|ol > li > ul|ol > li > ul|ol > li > ul|ol > li > ol > li:fresh +""") + diff --git a/tests/conversion_tests.py b/tests/conversion_tests.py index e3b4c9e..5912a0e 100644 --- a/tests/conversion_tests.py +++ b/tests/conversion_tests.py @@ -40,7 +40,7 @@ def paragraphs_are_converted_by_satisfying_matching_paths(): documents.paragraph(style_name="TipsParagraph", children=[ _run_with_text("Tip") ]), - styles=[ + style_map=[ style_reader.read_style("p.TipsParagraph => p.tip") ] ) @@ -63,7 +63,7 @@ def default_paragraph_style_is_specified_by_mapping_plain_paragraphs(): documents.paragraph(style_name="TipsParagraph", children=[ _run_with_text("Tip") ]), - styles=[ + style_map=[ style_reader.read_style("p => p.tip") ] ) @@ -94,7 +94,7 @@ def bulleted_paragraphs_are_converted_using_matching_styles(): documents.paragraph(children=[ _run_with_text("Hello") ], numbering=documents.numbering_level(level_index=0, is_ordered=False)), - styles=[ + style_map=[ style_reader.read_style("p:unordered-list(1) => ul > li:fresh") ] ) @@ -107,7 +107,7 @@ def bulleted_styles_dont_match_plain_paragraph(): documents.paragraph(children=[ _run_with_text("Hello") ]), - styles=[ + style_map=[ style_reader.read_style("p:unordered-list(1) => ul > li:fresh") ] ) @@ -134,7 +134,7 @@ def italic_runs_are_wrapped_in_emphasis_tags(): def runs_are_converted_by_satisfying_matching_paths(): result = convert_document_element_to_html( documents.run(style_name="TipsRun", children=[documents.Text("Tip")]), - styles=[ + style_map=[ style_reader.read_style("r.TipsRun => span.tip") ] ) |