b83e24e2f7
md2txt is a suite of minimal text-based markup exporters, and every other
renderer in it (text, micron, ama, gemini, nex) is a straight transform of
a document into a flat text format. The WML renderer is neither: it emits
an XML tree, and it restructures the document rather than transforming it
-- splitting one file into many <card>s, inventing navigation between
them, building a menu card that exists in no source document, and
paginating on a byte budget. That is why it needed levers no sibling
renderer needed, and why it alone forced a CARD_BREAK block kind and a
{.card} directive into the shared parser that every other renderer
ignores.
wapdown is that renderer given a repository of its own, where
restructuring a document into a navigable deck is the point.
Ported: the Markdown parser, block event models, and pipeline core, each
trimmed to what a deck compiler actually uses (no FIGlet, no hyphenation,
no ASCII-art includes, no text-layout frontmatter), plus the eight inline
regexes the renderer had been borrowing from a 1039-line text renderer.
The plugin registry comes along so other WAP-era targets can register
alongside wml later. Zero runtime dependencies.
Config is now first-class: every lever is an argparse flag with
validation and a frontmatter equivalent, layered CLI > frontmatter >
default, replacing the generic --renderer-option KEY=VALUE passthrough.
Five defects found while reading the code, each with a regression test:
- Link and image URLs were shredded by the emphasis patterns, which ran
before LINK_RE: a path like /v1_2_3/ became /v1<i>2</i>3/ inside the
href. Links and images are now resolved and stashed first.
- <table> was emitted as a direct child of <card>. The WML 1.3 content
model is (onevent*, timer?, (do | p | pre)*), so it must sit in a <p>.
- Link labels carried emphasis, but <a> is declared (#PCDATA | br | img)*
-- there is nowhere valid for a <b> inside one. Markers are now stripped.
- The menu card was built directly and never byte-packed, so the one card
most likely to be large was the one card exempt from the budget.
- Output was written with CRLF line endings. WML is XML served over HTTP.
New, WAP-idiomatic rather than Markdown-idiomatic:
- deck-level <template> hoisting nav that would otherwise repeat per card
- <select> menus, picked with a keypad digit instead of scrolled to
- --deck-per-card, one file per section cross-linked by filename, which
is the real answer to per-deck cache limits
- <head> metadata: Cache-Control max-age and <access>
- a Home options softkey, which <prev/> alone cannot provide
- an image policy (keep/alt/drop) for the WBMP-only reality of WAP 1.x
browsers -- no conversion is performed
186 tests, where neither repo had any. Golden files pin whole-document
output; every deck is validated against the real WML 1.3 DTD, vendored at
tests/dtd/wml13.dtd. Rendering examples/trail.md still matches md2txt's
committed output byte for byte, modulo the CRLF fix.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
94 lines
3.5 KiB
Python
94 lines
3.5 KiB
Python
"""Inline markup mapping and WML's escaping rules."""
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from wapdown.renderers.wml.inline import escape_wml, process_inline
|
|
|
|
|
|
class TestEscaping:
|
|
def test_xml_significant_characters(self):
|
|
assert escape_wml('a & b < c > d "e"') == "a & b < c > d "e""
|
|
|
|
def test_dollar_is_doubled(self):
|
|
# WML uses $ to introduce a variable substitution, so a literal $
|
|
# must be written $$ or the device eats the following word.
|
|
assert escape_wml("Permit fee: $5") == "Permit fee: $$5"
|
|
|
|
def test_ampersand_escaped_before_other_entities(self):
|
|
assert escape_wml("<") == "<"
|
|
assert "&lt;" not in escape_wml("a & b")
|
|
|
|
|
|
class TestEmphasis:
|
|
@pytest.mark.parametrize(
|
|
("source", "expected"),
|
|
[
|
|
("**bold**", "<b>bold</b>"),
|
|
("__bold__", "<b>bold</b>"),
|
|
("*italic*", "<i>italic</i>"),
|
|
("_italic_", "<i>italic</i>"),
|
|
("~~struck~~", "struck"), # no WML equivalent, markers dropped
|
|
("`code`", "code"),
|
|
],
|
|
)
|
|
def test_mapping(self, source, expected):
|
|
assert process_inline(source) == expected
|
|
|
|
def test_code_span_contents_are_not_reinterpreted(self):
|
|
assert process_inline("`a *b* c`") == "a *b* c"
|
|
|
|
|
|
class TestLinks:
|
|
def test_basic_link(self):
|
|
assert process_inline("[call](tel:+15555550123)") == (
|
|
'<a href="tel:+15555550123">call</a>'
|
|
)
|
|
|
|
def test_underscores_in_url_survive(self):
|
|
# Regression: emphasis patterns used to run before LINK_RE, so
|
|
# UNDERLINE_EM_RE shredded `v1_2_3` into `v1<i>2</i>3` inside the href.
|
|
result = process_inline("[notes](https://example.com/v1_2_3/x.html)")
|
|
assert result == '<a href="https://example.com/v1_2_3/x.html">notes</a>'
|
|
assert "<i>" not in result
|
|
|
|
def test_asterisks_in_url_survive(self):
|
|
result = process_inline("[log](https://ci.example.com/job/a*b*c/log)")
|
|
assert "a*b*c" in result
|
|
assert "<i>" not in result
|
|
|
|
def test_label_emphasis_is_stripped_not_translated(self):
|
|
# WML 1.3 declares <a> as (#PCDATA | br | img)*: there is nowhere
|
|
# valid to put a <b> inside a link label.
|
|
assert process_inline("[**go** now](http://x.test/)") == (
|
|
'<a href="http://x.test/">go now</a>'
|
|
)
|
|
|
|
def test_url_is_escaped_for_attribute_use(self):
|
|
assert process_inline("[q](http://x.test/?a=1&b=2)") == (
|
|
'<a href="http://x.test/?a=1&b=2">q</a>'
|
|
)
|
|
|
|
|
|
class TestImages:
|
|
def test_keep_is_the_default(self):
|
|
assert process_inline("") == '<img src="map.png" alt="Map"/>'
|
|
|
|
def test_alt_policy_replaces_non_wbmp(self, capsys):
|
|
assert process_inline("", images="alt") == "Map"
|
|
assert "non-WBMP" in capsys.readouterr().err
|
|
|
|
def test_drop_policy_removes_non_wbmp(self, capsys):
|
|
assert process_inline("", images="drop") == ""
|
|
assert "dropped" in capsys.readouterr().err
|
|
|
|
@pytest.mark.parametrize("policy", ["alt", "drop"])
|
|
def test_wbmp_always_survives(self, policy):
|
|
result = process_inline("", images=policy)
|
|
assert result == '<img src="icon.wbmp" alt="Icon"/>'
|
|
|
|
def test_wbmp_detected_past_a_query_string(self):
|
|
assert '<img' in process_inline("", images="drop")
|
|
|
|
def test_image_is_not_parsed_as_a_link(self):
|
|
assert process_inline("").startswith("<img")
|