mdhtml2docx 0.1.2__tar.gz → 0.1.3__tar.gz

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/CHANGELOG.md

@@ -1,5 +1,8 @@
 <!-- do not remove -->
 
+## 0.1.3
+
+
 ## 0.1.2
 
 ### New Features

{mdhtml2docx-0.1.2/mdhtml2docx.egg-info → mdhtml2docx-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mdhtml2docx
-Version: 0.1.2
+Version: 0.1.3
 Summary: Convert MDHTML to Word docx files
 Author-email: Jeremy Howard <j@fast.ai>
 License-Expression: Apache-2.0
@@ -30,21 +30,21 @@ MDHTML accepts the full HTML vocabulary. This exporter supports the portable ele
 ## Usage
 
 ```python
-from mdhtml import to_mdhtml
-from mdhtml2docx import convert
+from mdhtml import md2mdhtml
+from mdhtml2docx import mdhtml2docx
 
-html = to_mdhtml(markdown_text)
-warnings = convert(html, 'out.docx')
+html = md2mdhtml(markdown_text)
+warnings = mdhtml2docx(html, 'out.docx')
 ```
 
-`convert` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.parse_mdhtml`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
+`mdhtml2docx` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.mdhtml2dom`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
 
 ```python
-from mdhtml import parse_mdhtml
+from mdhtml import mdhtml2dom
 
-document = parse_mdhtml(html)
+document = mdhtml2dom(html)
 document.children[0].attrs['custom-style'] = 'Contract Title'
-warnings = convert(document, 'out.docx')
+warnings = mdhtml2docx(document, 'out.docx')
 ```
 
 Body-position text and phrasing content become implicit Word paragraphs. Whitespace between blocks remains inert. HTML templates remain inert and are not rendered.
@@ -89,7 +89,7 @@ The word before the number comes from the reference's type, the id up to its fir
 
 Number fields need numbered headings. If your reference docx already numbers its heading styles (most firm templates do), nothing more is required, and the converter leaves that numbering alone. Otherwise pass `number_headings='legal'` for 1. / (a) / (i) numbering or `'decimal'` for 1 / 1.1 / 1.1.1 (the names index `styles.SCHEMES`), or pass your own scheme as a `{lvlText: numFmt}` dict, one entry per heading level. A reference-list entry ending in `.xml` is a third route: a raw file of `w:style`, `w:abstractNum`, and `w:num` elements contributing styles and numbering together, with ids remapped to avoid collisions.
 
-Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at convert time.
+Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at conversion time.
 
 ## Validation
 

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/README.md

@@ -9,21 +9,21 @@ MDHTML accepts the full HTML vocabulary. This exporter supports the portable ele
 ## Usage
 
 ```python
-from mdhtml import to_mdhtml
-from mdhtml2docx import convert
+from mdhtml import md2mdhtml
+from mdhtml2docx import mdhtml2docx
 
-html = to_mdhtml(markdown_text)
-warnings = convert(html, 'out.docx')
+html = md2mdhtml(markdown_text)
+warnings = mdhtml2docx(html, 'out.docx')
 ```
 
-`convert` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.parse_mdhtml`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
+`mdhtml2docx` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.mdhtml2dom`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
 
 ```python
-from mdhtml import parse_mdhtml
+from mdhtml import mdhtml2dom
 
-document = parse_mdhtml(html)
+document = mdhtml2dom(html)
 document.children[0].attrs['custom-style'] = 'Contract Title'
-warnings = convert(document, 'out.docx')
+warnings = mdhtml2docx(document, 'out.docx')
 ```
 
 Body-position text and phrasing content become implicit Word paragraphs. Whitespace between blocks remains inert. HTML templates remain inert and are not rendered.
@@ -68,7 +68,7 @@ The word before the number comes from the reference's type, the id up to its fir
 
 Number fields need numbered headings. If your reference docx already numbers its heading styles (most firm templates do), nothing more is required, and the converter leaves that numbering alone. Otherwise pass `number_headings='legal'` for 1. / (a) / (i) numbering or `'decimal'` for 1 / 1.1 / 1.1.1 (the names index `styles.SCHEMES`), or pass your own scheme as a `{lvlText: numFmt}` dict, one entry per heading level. A reference-list entry ending in `.xml` is a third route: a raw file of `w:style`, `w:abstractNum`, and `w:num` elements contributing styles and numbering together, with ids remapped to avoid collisions.
 
-Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at convert time.
+Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at conversion time.
 
 ## Validation
 

mdhtml2docx-0.1.3/mdhtml2docx/__init__.py

@@ -0,0 +1,6 @@
+__version__ = "0.1.3"
+
+
+
+
+from .mdhtml2docx import mdhtml2docx

mdhtml2docx-0.1.2/mdhtml2docx/convert.py → mdhtml2docx-0.1.3/mdhtml2docx/mdhtml2docx.py

@@ -9,7 +9,7 @@ from copy import deepcopy
 from pathlib import Path
 from fast5ever import Comment, Element, Node, Text
 from lxml import etree
-from mdhtml import parse_mdhtml
+from mdhtml import mdhtml2dom
 from mdhtml.export import REFTYPES, SCHEMES, decode_raw, tmpl_node, group_plan, ref_tokens, ref_variant, target_kind, Resolver
 from .styles import STYLE_MAP, style_id, theme_styles
 from .styles import ref_path as _refpath
@@ -17,7 +17,7 @@ from .wml import *
 from .wml import qn
 from .hilite import segments, tokenize
 
-__all__ = ['convert', 'mustache_fields']
+__all__ = ['mdhtml2docx', 'mustache_fields']
 
 def _sid(key): return style_id(STYLE_MAP[key])
 
@@ -38,7 +38,7 @@ def parse_frag(src):
     "Parse an MDHTML body fragment, or return an existing mutable fragment"
     if isinstance(src, Node): return src
     if not isinstance(src, str): raise TypeError('input must be an MDHTML string or fast5ever node')
-    return parse_mdhtml(src)
+    return mdhtml2dom(src)
 
 class Converter:
     def __init__(self, reference=None, base=None, reftypes=None, number_headings=None, tmpl=None):
@@ -604,13 +604,17 @@ class Converter:
     BIND_ID = '{8E2C9A44-7D31-4E5B-9C0D-1A6F2B3C4D5E}'   # fixed datastore id, so builds are reproducible
 
     def tmpl_runs(self, el, fmt, form):
-        """Template-token runs. Range markers and unknown tokens are converter policy: literal
-        `«body»` runs, so an unfilled form shows its markers. Var tokens go through the `tmpl`
-        callable with the token node dict (see `mdhtml.export.tmpl_node`): str is a literal text
+        """Template-instruction runs. Non-value Mustache operations are converter policy: literal
+        marker runs, so an unfilled form shows its structure. Value operations go through the `tmpl`
+        callable with the semantic node dict (see `mdhtml.export.tmpl_node`): str is a literal text
         run, ('field', instr) a live field, ('control', name) an interactive plain-text content
         control, ('bound', name) a data-bound one, None dropped"""
+        if 'data-op' not in el.attrs: return []
         node = tmpl_node(el, form)
-        if node["kind"] != "var": return self.text_runs(f'«{node["body"].strip()}»', fmt)
+        action = node['op'].rsplit(':', 1)[-1]
+        if action != 'value':
+            marker = dict(section='#', inverted='^', end='/').get(action, '')
+            return self.text_runs(f'«{marker}{node["value"]}»', fmt)
         if self.tmpl is None: return []
         res = self.tmpl(node)
         if res is None: return []
@@ -618,7 +622,7 @@ class Converter:
         kind, val = res
         if kind == 'field':
             self.has_fields = True
-            return [E('w:fldSimple', {'w:instr': f' {val.strip()} '}, E('w:r', self.rpr(fmt), E('w:t', f'«{node["name"]}»')))]
+            return [E('w:fldSimple', {'w:instr': f' {val.strip()} '}, E('w:r', self.rpr(fmt), E('w:t', f'«{node["value"]}»')))]
         if kind in ('control', 'bound'):
             self.has_controls = True
             sdtpr = E('w:sdtPr', E('w:alias', {'w:val': val}), E('w:tag', {'w:val': val}), E('w:showingPlcHdr'))
@@ -903,11 +907,11 @@ class Converter:
 
 def mustache_fields(node):
     "Template variables as live Word `MERGEFIELD`s (markers never reach `tmpl`: the converter shows them literally)"
-    return 'field', f'MERGEFIELD {node["name"]}'
+    return 'field', f'MERGEFIELD {node["value"]}'
 
 
 
-def convert(mdhtml, dest, reference=None, base=None, reftypes=None, number_headings=None, tmpl=None):
+def mdhtml2docx(mdhtml, dest, reference=None, base=None, reftypes=None, number_headings=None, tmpl=None):
     """Convert an MDHTML string or mutable fast5ever DOM to a docx file at `dest`; returns warnings.
     `reference` is a reference docx path, or a list of them: the first supplies the whole archive
     (default, or when None: the built-in template), later entries contribute styles only, later-wins -
@@ -917,9 +921,9 @@ def convert(mdhtml, dest, reference=None, base=None, reftypes=None, number_headi
     resolve against `base` ('.'). Cross-references (`data-ref` anchors from Markdown `[@sec-x]`) become
     live REF fields; `reftypes` maps type tokens to (singular, plural) prefix words beyond the built-in
     `sec`, and `number_headings` (a styles.SCHEMES name such as 'legal', or a {lvlText: numFmt} dict, one entry per heading level)
-    numbers the headings via a multilevel list so `\\w` fields resolve. Template tokens are dropped
-    unless `tmpl` is given: a callable taking the token node dict (`mdhtml.export.tmpl_node`: `body`,
-    `syntax`, `form`, `kind`, `name`, `inverted`) and returning a str for a literal text run,
+    numbers the headings via a multilevel list so `\\w` fields resolve. Template value instructions are dropped
+    unless `tmpl` is given; other operations remain visible markers. `tmpl` is a callable taking the semantic instruction dict
+    (`mdhtml.export.tmpl_node`: `op`, `value`, `form`) and returning a str for a literal text run,
     `('field', instr)` for a live field, `('control', name)` for an interactive plain-text content
     control, `('bound', name)` for a content control data-bound to a shared per-variable XML node
     (same-name controls stay in sync as one is filled), or None to drop; range markers never reach `tmpl` and render as literal «body» runs - `mustache_fields` here

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/mdhtml2docx/wml.py

@@ -1,7 +1,7 @@
 """WordprocessingML construction helpers: namespaces, a qualified-name element builder, unit
 conversions, and the colwidths track-list parser. Child-element order inside w:pPr/w:rPr/w:tcPr
 etc follows the ECMA-376 content models; builders here emit children in the order callers pass
-them, so callers are responsible for schema order (the convert module's helpers encode it)."""
+them, so callers are responsible for schema order (the mdhtml2docx module's helpers encode it)."""
 import re, struct
 from xml.sax.saxutils import escape
 from lxml import etree

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3/mdhtml2docx.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mdhtml2docx
-Version: 0.1.2
+Version: 0.1.3
 Summary: Convert MDHTML to Word docx files
 Author-email: Jeremy Howard <j@fast.ai>
 License-Expression: Apache-2.0
@@ -30,21 +30,21 @@ MDHTML accepts the full HTML vocabulary. This exporter supports the portable ele
 ## Usage
 
 ```python
-from mdhtml import to_mdhtml
-from mdhtml2docx import convert
+from mdhtml import md2mdhtml
+from mdhtml2docx import mdhtml2docx
 
-html = to_mdhtml(markdown_text)
-warnings = convert(html, 'out.docx')
+html = md2mdhtml(markdown_text)
+warnings = mdhtml2docx(html, 'out.docx')
 ```
 
-`convert` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.parse_mdhtml`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
+`mdhtml2docx` takes an MDHTML string, writes a docx, and returns a list of warning strings. It parses strings with `mdhtml.mdhtml2dom`, so normal HTML5 repair applies and XML well-formedness is irrelevant. It also accepts an existing mutable fast5ever DOM:
 
 ```python
-from mdhtml import parse_mdhtml
+from mdhtml import mdhtml2dom
 
-document = parse_mdhtml(html)
+document = mdhtml2dom(html)
 document.children[0].attrs['custom-style'] = 'Contract Title'
-warnings = convert(document, 'out.docx')
+warnings = mdhtml2docx(document, 'out.docx')
 ```
 
 Body-position text and phrasing content become implicit Word paragraphs. Whitespace between blocks remains inert. HTML templates remain inert and are not rendered.
@@ -89,7 +89,7 @@ The word before the number comes from the reference's type, the id up to its fir
 
 Number fields need numbered headings. If your reference docx already numbers its heading styles (most firm templates do), nothing more is required, and the converter leaves that numbering alone. Otherwise pass `number_headings='legal'` for 1. / (a) / (i) numbering or `'decimal'` for 1 / 1.1 / 1.1.1 (the names index `styles.SCHEMES`), or pass your own scheme as a `{lvlText: numFmt}` dict, one entry per heading level. A reference-list entry ending in `.xml` is a third route: a raw file of `w:style`, `w:abstractNum`, and `w:num` elements contributing styles and numbering together, with ids remapped to avoid collisions.
 
-Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at convert time.
+Figures and captioned tables number themselves with SEQ fields: a figure renders as its image plus a "Figure 1: caption" paragraph below (caption style), a table caption as "Table 1: caption" above the table, both live. When the element has an id, the label-and-number span is bookmarked, so `[@fig-plot]` inserts a live "Figure 1" (no extra prefix word; the label is part of the bookmarked text) and `[-@tbl-stages]` the bare number via a second number-only bookmark. `fig` and `tbl` are built-in reftypes alongside `sec`, and their label words come from the same table. Mixed-type groups render each item with its own singular prefix ("Figure 1 and Table 2"); same-type groups pluralize once. Reference targets must be things that get bookmarks - headings, paragraphs, figures, and tables with ids - and a ref to anything else is an error at conversion time.
 
 ## Validation
 

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/mdhtml2docx.egg-info/SOURCES.txt

@@ -5,8 +5,8 @@ README.md
 pyproject.toml
 mdhtml2docx/__init__.py
 mdhtml2docx/asvocab.py
-mdhtml2docx/convert.py
 mdhtml2docx/hilite.py
+mdhtml2docx/mdhtml2docx.py
 mdhtml2docx/styles.py
 mdhtml2docx/validate.py
 mdhtml2docx/wml.py

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/tests/test_convert.py

@@ -4,10 +4,10 @@ from pathlib import Path
 from fastcore.test import test_eq as teq, test as tt, test_fail as tfail
 from fastcore.utils import in_
 
-from mdhtml import DASHES, replacements, parse_mdhtml, to_mdhtml
+from mdhtml import DASHES, replacements, mdhtml2dom, md2mdhtml
 from mdhtml.mustache import MUSTACHE
 from mdhtml.tools import SAMPLE_MD, sample_md
-from mdhtml2docx.convert import convert, mustache_fields
+from mdhtml2docx.mdhtml2docx import mdhtml2docx, mustache_fields
 from mdhtml2docx.validate import fast_checks
 
 
@@ -20,7 +20,7 @@ def pandoc(path, to='markdown'):
 
 def test_skeleton(tmp_path):
     out = tmp_path/'t.docx'
-    convert('<p>Hello <em>world</em> with <strong>bold</strong> and <strong><em>both</em></strong>.</p>\n'
+    mdhtml2docx('<p>Hello <em>world</em> with <strong>bold</strong> and <strong><em>both</em></strong>.</p>\n'
         '<p>Second para.</p>', out)
     teq(fast_checks(out), 'valid')
     md = pandoc(out)
@@ -33,28 +33,28 @@ def test_skeleton(tmp_path):
 
 def test_dash_replacements(tmp_path):
     out = tmp_path/'t.docx'
-    convert(to_mdhtml('scores 3--5 -- nice... `a--b`', callbacks={'text': replacements(*DASHES)}), out)
+    mdhtml2docx(md2mdhtml('scores 3--5 -- nice... `a--b`', callbacks={'text': replacements(*DASHES)}), out)
     doc = zipfile.ZipFile(out).read('word/document.xml').decode()
     for s in ('3–5', ' – nice… ', 'a--b'): tt(s, doc, in_)
 
 
 def test_html5_fragment_and_mutable_dom_input(tmp_path):
     out = tmp_path/'t.docx'
-    dom = parse_mdhtml('<p>Before <div>middle</div> after.</p><span zoop:33="x">tail</span>'
+    dom = mdhtml2dom('<p>Before <div>middle</div> after.</p><span zoop:33="x">tail</span>'
         '<!-- this is a -- comment --><input type="date"><template><p>hidden</p></template>')
     dom.children[1].attrs['data-kind'] = 'changed'
-    warns = convert(dom, out)
+    warns = mdhtml2docx(dom, out)
     teq(warns, ["unhandled inline <input type='date'>; dropped"])
     md = pandoc(out)
     for s in ('Before', 'middle', 'after.', 'tail'): tt(s, md, in_)
     assert 'hidden' not in md
-    convert('<template><p>still hidden</p></template>', out)
+    mdhtml2docx('<template><p>still hidden</p></template>', out)
     assert '<w:p>' not in zipfile.ZipFile(out).read('word/document.xml').decode()
 
 
 def test_basic_blocks(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(
+    warns = mdhtml2docx(
         '<h1 id="top">Title</h1>\n<h2>Sub <em>title</em></h2>\n'
         '<p>Call <code>f(x)</code> or see <a href="https://fast.ai/">fast.ai</a> '
         'and <a href="#top">the title</a>.</p>\n'
@@ -72,7 +72,7 @@ def test_basic_blocks(tmp_path):
 
 def test_lists(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(
+    warns = mdhtml2docx(
         '<ul>\n<li>one</li>\n<li>two\n<ul>\n<li>deep</li>\n</ul>\n</li>\n</ul>\n'
         '<ol>\n<li>first</li>\n<li>second</li>\n</ol>\n'
         '<ol start="5">\n<li>fifth</li>\n</ol>\n'
@@ -91,7 +91,7 @@ def test_lists(tmp_path):
 
 def test_tables(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(
+    warns = mdhtml2docx(
         '<table colwidths="10em 2fr 1fr">\n<thead>\n'
         '<tr><th align="left">Feature</th><th align="center">Status</th><th align="right">Notes</th></tr>\n'
         '</thead>\n<tbody>\n'
@@ -116,7 +116,7 @@ def test_tables(tmp_path):
 def test_more_features(tmp_path):
     out = tmp_path/'t.docx'
     img = Path(__file__).parent/'fixtures'/'tiny.png'
-    warns = convert(
+    warns = mdhtml2docx(
         '<p>H<sub>2</sub>O, E=mc<sup>2</sup>, <del>gone</del>, <mark>hot</mark>, <u>under</u>.</p>\n'
         '<hr>\n'
         '<dl>\n<dt>term</dt>\n<dd>definition here</dd>\n</dl>\n'
@@ -162,7 +162,7 @@ def test_imgsize():
 
 def test_math(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert('<p>Euler: <span class="math inline">e^{i\\pi} + 1 = 0</span> inline.</p>\n'
+    warns = mdhtml2docx('<p>Euler: <span class="math inline">e^{i\\pi} + 1 = 0</span> inline.</p>\n'
         '<div class="math display">E = mc^2</div>', out)
     teq(warns, [])
     teq(fast_checks(out), 'valid')
@@ -180,7 +180,7 @@ def test_sample(tmp_path):
     from lxml import etree
     from mdhtml2docx.styles import STYLE_MAP, style_id
     out = tmp_path/'sample.docx'
-    warns = convert(to_mdhtml(sample_md(), callbacks={'text': replacements(*DASHES)}, implicit_figures=True), out, base=SAMPLE_MD.parent, number_headings='legal')
+    warns = mdhtml2docx(md2mdhtml(sample_md(), callbacks={'text': replacements(*DASHES)}, implicit_figures=True), out, base=SAMPLE_MD.parent, number_headings='legal')
     teq(warns, [])
     teq(fast_checks(out), 'valid')
     W = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
@@ -207,7 +207,7 @@ def test_sample(tmp_path):
 def test_code_highlight(tmp_path):
     "fastpylight scopes: language-classed blocks get Hl* character styles from the theme ref; text still round-trips"
     out = tmp_path/'t.docx'
-    warns = convert('<pre><code class="language-python">def f(x):\n    return "hi"\n</code></pre>\n'
+    warns = mdhtml2docx('<pre><code class="language-python">def f(x):\n    return "hi"\n</code></pre>\n'
         '<pre><code>no language here</code></pre>', out)
     teq(warns, [])
     teq(fast_checks(out), 'valid')
@@ -228,7 +228,7 @@ def test_theme_refs(tmp_path):
     from mdhtml2docx.styles import ref_path, theme_ref
     mdhtml = '<pre><code class="language-python">def f(x):\n    return x\n</code></pre>'
     out = tmp_path/'t.docx'
-    convert(mdhtml, out, reference=[ref_path(), 'dracula'])
+    mdhtml2docx(mdhtml, out, reference=[ref_path(), 'dracula'])
     teq(fast_checks(out), 'valid')
     styles = zipfile.ZipFile(out).read('word/styles.xml').decode()
     tt('w:styleId="HlKeyword"', styles, in_)
@@ -240,12 +240,12 @@ def test_theme_refs(tmp_path):
     ref = theme_ref('dracula', tmp_path/'dracula.docx')
     teq(fast_checks(ref), 'valid')
     out2 = tmp_path/'t2.docx'
-    convert(mdhtml, out2, reference=[ref_path(), ref])
+    mdhtml2docx(mdhtml, out2, reference=[ref_path(), ref])
     ids = lambda p: sorted(s.split('"')[1] for s in zipfile.ZipFile(p).read('word/styles.xml').decode().split('w:styleId=')[1:])
     teq(ids(out2), ids(out))
     # single custom reference (no theme entry) = plain code
     out3 = tmp_path/'t3.docx'
-    convert(mdhtml, out3, reference=ref_path())
+    mdhtml2docx(mdhtml, out3, reference=ref_path())
     assert 'HlKeyword' not in zipfile.ZipFile(out3).read('word/document.xml').decode()
 
 
@@ -262,7 +262,7 @@ def test_segments_scopes():
 def test_raw_docx(tmp_path):
     out = tmp_path/'t.docx'
     b64 = base64.b64encode(b'<w:r><w:t>B64</w:t></w:r>').decode()
-    warns = convert(
+    warns = mdhtml2docx(
         '<p>before</p>\n'
         '<script type="application/vnd.mdhtml.raw" data-format="docx"><w:p><w:r><w:br w:type="page"/></w:r></w:p></script>\n'
         '<p>a <script type="application/vnd.mdhtml.raw" data-format="docx" data-encoding="html">&lt;w:r&gt;&lt;w:t&gt;RAW&lt;/w:t&gt;&lt;/w:r&gt;</script> b</p>\n'
@@ -275,17 +275,17 @@ def test_raw_docx(tmp_path):
     md = pandoc(out)
     for s in ('a RAW b', 'B64'): tt(s, md, in_)
     assert 'newpage' not in doc  # unrecognized format dropped
-    warns = convert('<script type="application/vnd.mdhtml.raw" data-format="docx"><w:oops></script>', out)
+    warns = mdhtml2docx('<script type="application/vnd.mdhtml.raw" data-format="docx"><w:oops></script>', out)
     teq(len(warns), 1)
     tt('malformed', warns[0], in_)
-    warns = convert('<script type="application/vnd.mdhtml.raw" data-format="docx" data-encoding="base64">!!!</script>', out)
+    warns = mdhtml2docx('<script type="application/vnd.mdhtml.raw" data-format="docx" data-encoding="base64">!!!</script>', out)
     teq(len(warns), 1)
     tt('malformed base64', warns[0], in_)
 
 
 def test_xrefs(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(
+    warns = mdhtml2docx(
         '<h1 id="sec-intro">Intro</h1>\n<h2 id="sec-pay">Payment terms</h2>\n'
         '<p>See <a href="#sec-pay" data-ref=""></a> and <a href="#sec-intro" data-ref="bare"></a>, '
         'per <a href="#sec-pay" data-ref="">Clause</a>, also '
@@ -302,15 +302,15 @@ def test_xrefs(tmp_path):
     for s in ('lowerLetter', '(%2)', 'Heading1'): tt(s, num, in_)
     tt('updateFields', zipfile.ZipFile(out).read('word/settings.xml').decode(), in_)
     tt('w:numPr', zipfile.ZipFile(out).read('word/styles.xml').decode(), in_)
-    tfail(lambda: convert('<p><a href="#nope" data-ref=""></a></p>', out), contains='#nope')
-    tfail(lambda: convert('<p id="z-a"><a href="#z-a" data-ref=""></a></p>', out),
+    tfail(lambda: mdhtml2docx('<p><a href="#nope" data-ref=""></a></p>', out), contains='#nope')
+    tfail(lambda: mdhtml2docx('<p id="z-a"><a href="#z-a" data-ref=""></a></p>', out),
         contains="reference type 'z'")
-    tfail(lambda: convert('<p><a href="#sec-pay" data-ref="page text"></a></p>', out), contains='conflicting data-ref')
+    tfail(lambda: mdhtml2docx('<p><a href="#sec-pay" data-ref="page text"></a></p>', out), contains='conflicting data-ref')
 
 
 def test_text_targets(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(
+    warns = mdhtml2docx(
         '<h1 id="sec-d">Defs</h1>\n'
         '<dl><dt id="def-term"><strong>"Term"</strong></dt><dt id="def-ap">Agreement Period</dt>'
         '<dd>the deal period</dd></dl>\n'
@@ -326,9 +326,9 @@ def test_text_targets(tmp_path):
 def test_xrefs_numbered_reference_doc(tmp_path):
     "A numbered docx (made by us) as reference: numbering merges with list numbering, no reinjection"
     ref = tmp_path/'ref.docx'
-    convert('<h1 id="a">A</h1>', ref, number_headings='legal')
+    mdhtml2docx('<h1 id="a">A</h1>', ref, number_headings='legal')
     out = tmp_path/'t.docx'
-    warns = convert('<h1 id="sec-a">A</h1>\n<ul>\n<li>one</li>\n</ul>\n'
+    warns = mdhtml2docx('<h1 id="sec-a">A</h1>\n<ul>\n<li>one</li>\n</ul>\n'
         '<p>See <a href="#sec-a" data-ref=""></a>.</p>', out, reference=ref)
     teq(warns, [])
     teq(fast_checks(out), 'valid')
@@ -351,7 +351,7 @@ def test_xml_contributor(tmp_path):
         '<w:pPr><w:numPr><w:ilvl w:val="0"/><w:numId w:val="1"/></w:numPr></w:pPr>'
         '</w:style></w:styles>')
     out = tmp_path/'t.docx'
-    warns = convert('<p custom-style="Fancy">Hi</p>\n<ul>\n<li>one</li>\n</ul>', out,
+    warns = mdhtml2docx('<p custom-style="Fancy">Hi</p>\n<ul>\n<li>one</li>\n</ul>', out,
         reference=[None, xml])
     teq(warns, [])
     teq(fast_checks(out), 'valid')
@@ -365,7 +365,7 @@ def test_caption_refs(tmp_path):
     "Figures and captioned tables: SEQ-numbered captions, label+number bookmarks, fig/tbl refs"
     out = tmp_path/'t.docx'
     img = Path(__file__).parent/'fixtures'/'tiny.png'
-    warns = convert(
+    warns = mdhtml2docx(
         f'<figure id="fig-plot" class="wide"><img src="{img}" alt=""><figcaption>A plot</figcaption></figure>\n'
         '<table id="tbl-r"><caption>Results <em>now</em></caption><thead><tr><th>a</th></tr></thead>'
         '<tbody><tr><td>1</td></tr></tbody></table>\n'
@@ -382,17 +382,17 @@ def test_caption_refs(tmp_path):
     md = pandoc(out)
     tt('A plot', md, in_)
     # a ref to an id that never becomes a bookmark is an error, not a dud field
-    tfail(lambda: convert('<div id="d-x"><p>hi</p></div><p><a href="#d-x" data-ref=""></a></p>', out),
+    tfail(lambda: mdhtml2docx('<div id="d-x"><p>hi</p></div><p><a href="#d-x" data-ref=""></a></p>', out),
         contains='#d-x')
 
 
 def test_template_tokens(tmp_path):
     out = tmp_path/'t.docx'
-    src = to_mdhtml('Pay {{sal}} to {{name}}.\n\n{{#opt}}\n\nGranted.\n\n{{/opt}}\n', templates=MUSTACHE)
-    convert(src, out)                                    # default: vars dropped, markers literal
+    src = md2mdhtml('Pay {{sal}} to {{name}}.\n\n{{#opt}}\n\nGranted.\n\n{{/opt}}\n', templates=MUSTACHE)
+    mdhtml2docx(src, out)                                    # default: vars dropped, markers literal
     doc = zipfile.ZipFile(out).read('word/document.xml').decode()
     assert 'sal' not in doc and '{{' not in doc and '«#opt»' in doc   # vars dropped; markers stay visible
-    warns = convert(src, out, tmpl=mustache_fields)
+    warns = mdhtml2docx(src, out, tmpl=mustache_fields)
     doc = zipfile.ZipFile(out).read('word/document.xml').decode()
     assert 'MERGEFIELD sal' in doc and 'MERGEFIELD name' in doc
     assert '«#opt»' in doc and '«/opt»' in doc          # markers: converter-rendered literals, own paragraphs
@@ -401,7 +401,7 @@ def test_template_tokens(tmp_path):
 
 def test_table_custom_style(tmp_path):
     out = tmp_path/'t.docx'
-    convert(to_mdhtml('| A |\n|---|\n| b |\n{: custom-style="Borderless Table"}\n\n| C |\n|---|\n| d |\n'), out)
+    mdhtml2docx(md2mdhtml('| A |\n|---|\n| b |\n{: custom-style="Borderless Table"}\n\n| C |\n|---|\n| d |\n'), out)
     doc = zipfile.ZipFile(out).read('word/document.xml').decode()
     tt('<w:tblStyle w:val="BorderlessTable"/>', doc, in_)          # styled table picks the reference style
     tt('<w:tblStyle w:val="TableGrid"/>', doc, in_)                # plain table keeps the default
@@ -411,9 +411,9 @@ def test_table_custom_style(tmp_path):
 
 
 def test_template_controls(tmp_path):
-    def controls(node): return 'control', node['name']
+    def controls(node): return 'control', node['value']
     out = tmp_path/'t.docx'
-    convert(to_mdhtml('Pay {{sal}} to {{name}}.\n\n{{#opt}}\n', templates=MUSTACHE), out, tmpl=controls)
+    mdhtml2docx(md2mdhtml('Pay {{sal}} to {{name}}.\n\n{{#opt}}\n', templates=MUSTACHE), out, tmpl=controls)
     doc = zipfile.ZipFile(out).read('word/document.xml').decode()
     assert doc.count('<w:sdt>') == 2 and 'w:val="sal"' in doc and 'w:val="name"' in doc
     assert doc.count('<w:showingPlcHdr/>') == 2 and 'w:val="PlaceholderText"' in doc
@@ -424,9 +424,9 @@ def test_template_controls(tmp_path):
 
 
 def test_template_bound(tmp_path):
-    def bound(node): return 'bound', node['name']
+    def bound(node): return 'bound', node['value']
     out = tmp_path/'t.docx'
-    convert(to_mdhtml('Pay {{sal}} to {{sal}} and {{name}}.\n', templates=MUSTACHE), out, tmpl=bound)
+    mdhtml2docx(md2mdhtml('Pay {{sal}} to {{sal}} and {{name}}.\n', templates=MUSTACHE), out, tmpl=bound)
     z = zipfile.ZipFile(out)
     doc = z.read('word/document.xml').decode()
     assert doc.count('<w:dataBinding ') == 3 and doc.count('/ns0:fields[1]/ns0:sal[1]') == 2
@@ -439,7 +439,7 @@ def test_template_bound(tmp_path):
 
 def test_details_degrades_to_bold_label(tmp_path):
     out = tmp_path/'t.docx'
-    warns = convert(to_mdhtml('::: {.details .tool-usage-details}\n## the label\n\nbody text\n:::\n'), out)
+    warns = mdhtml2docx(md2mdhtml('::: {.details .tool-usage-details}\n## the label\n\nbody text\n:::\n'), out)
     assert not warns
     md = pandoc(out)
     tt('**the label**', md, in_)

{mdhtml2docx-0.1.2 → mdhtml2docx-0.1.3}/tests/test_word.py

@@ -1,9 +1,9 @@
 import pytest
 from pathlib import Path
 
-from mdhtml import DASHES, replacements, to_mdhtml
+from mdhtml import DASHES, replacements, md2mdhtml
 from mdhtml.tools import SAMPLE_MD, sample_md
-from mdhtml2docx import convert
+from mdhtml2docx import mdhtml2docx
 
 DATA = Path(__file__).parent.parent/'_data'
 
@@ -12,6 +12,6 @@ pytestmark = [pytest.mark.slow, pytest.mark.checkout]
 
 def test_sample():
     docx = DATA/'sample.docx'
-    warns = convert(to_mdhtml(sample_md(), callbacks={'text': replacements(*DASHES)}, implicit_figures=True), docx, base=SAMPLE_MD.parent, number_headings='legal')
+    warns = mdhtml2docx(md2mdhtml(sample_md(), callbacks={'text': replacements(*DASHES)}, implicit_figures=True), docx, base=SAMPLE_MD.parent, number_headings='legal')
     assert not warns
     assert docx.stat().st_size

mdhtml2docx-0.1.2/mdhtml2docx/__init__.py

@@ -1,5 +0,0 @@
-__version__ = "0.1.2"
-
-
-
-from .convert import convert