Extract the WML exporter from md2txt into wapdown
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>
2026-09-23 09:27:49 +03:00
|
|
|
"""Configuration layering: CLI flag > frontmatter > default."""
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
from wapdown.config import DEFAULT_MAX_CARD_BYTES, ConfigError, DeckConfig
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestPrecedence:
|
|
|
|
|
def test_defaults_when_nothing_is_given(self):
|
|
|
|
|
config = DeckConfig.resolve()
|
|
|
|
|
assert config.split_level == 0
|
|
|
|
|
assert config.max_card_bytes == DEFAULT_MAX_CARD_BYTES
|
|
|
|
|
assert config.menu is True
|
|
|
|
|
assert config.menu_style == "links"
|
|
|
|
|
assert config.title is None
|
|
|
|
|
|
|
|
|
|
def test_frontmatter_beats_default(self):
|
|
|
|
|
config = DeckConfig.resolve({"split_level": "2", "title": "Trail"})
|
|
|
|
|
assert config.split_level == 2
|
|
|
|
|
assert config.title == "Trail"
|
|
|
|
|
|
|
|
|
|
def test_cli_beats_frontmatter(self):
|
|
|
|
|
config = DeckConfig.resolve({"split_level": "2"}, {"split_level": 3})
|
|
|
|
|
assert config.split_level == 3
|
|
|
|
|
|
|
|
|
|
def test_absent_cli_option_does_not_clobber_frontmatter(self):
|
|
|
|
|
# argparse hands every unset option through as None; that must mean
|
|
|
|
|
# "not given" rather than "set to nothing".
|
|
|
|
|
config = DeckConfig.resolve({"title": "Trail"}, {"title": None, "menu": None})
|
|
|
|
|
assert config.title == "Trail"
|
|
|
|
|
assert config.menu is True
|
|
|
|
|
|
|
|
|
|
def test_unknown_frontmatter_key_warns_but_does_not_fail(self, capsys):
|
|
|
|
|
config = DeckConfig.resolve({"hyphenate": "true", "title": "T"})
|
|
|
|
|
assert config.title == "T"
|
|
|
|
|
assert "unknown frontmatter key 'hyphenate'" in capsys.readouterr().err
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestCoercion:
|
|
|
|
|
@pytest.mark.parametrize("raw", ["true", "yes", "1", "on", "TRUE"])
|
|
|
|
|
def test_truthy_strings(self, raw):
|
|
|
|
|
assert DeckConfig.resolve({"menu": raw}).menu is True
|
|
|
|
|
|
|
|
|
|
@pytest.mark.parametrize("raw", ["false", "no", "0", "off", "FALSE"])
|
|
|
|
|
def test_falsy_strings(self, raw):
|
|
|
|
|
assert DeckConfig.resolve({"menu": raw}).menu is False
|
|
|
|
|
|
|
|
|
|
def test_menu_style_is_case_insensitive(self):
|
|
|
|
|
assert DeckConfig.resolve({"menu_style": "SELECT"}).menu_style == "select"
|
|
|
|
|
|
|
|
|
|
def test_hyphenated_frontmatter_key_is_accepted(self):
|
|
|
|
|
assert DeckConfig.resolve({"split-level": "2"}).split_level == 2
|
|
|
|
|
|
|
|
|
|
def test_empty_title_becomes_none(self):
|
|
|
|
|
assert DeckConfig.resolve({"title": ""}).title is None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestValidation:
|
|
|
|
|
@pytest.mark.parametrize("value", [-1, 7])
|
|
|
|
|
def test_split_level_out_of_range(self, value):
|
|
|
|
|
with pytest.raises(ConfigError, match="split_level"):
|
|
|
|
|
DeckConfig.resolve(overrides={"split_level": value})
|
|
|
|
|
|
|
|
|
|
def test_negative_byte_budget(self):
|
|
|
|
|
with pytest.raises(ConfigError, match="max_card_bytes"):
|
|
|
|
|
DeckConfig.resolve(overrides={"max_card_bytes": -1})
|
|
|
|
|
|
|
|
|
|
def test_unknown_menu_style(self):
|
|
|
|
|
with pytest.raises(ConfigError, match="menu_style"):
|
|
|
|
|
DeckConfig.resolve(overrides={"menu_style": "carousel"})
|
|
|
|
|
|
|
|
|
|
def test_unknown_image_policy(self):
|
|
|
|
|
with pytest.raises(ConfigError, match="images"):
|
|
|
|
|
DeckConfig.resolve(overrides={"images": "wbmp"})
|
|
|
|
|
|
|
|
|
|
def test_non_numeric_split_level_in_frontmatter(self):
|
|
|
|
|
# Previously an uncaught ValueError escaping as a traceback.
|
|
|
|
|
with pytest.raises(ConfigError, match="split_level must be a number"):
|
|
|
|
|
DeckConfig.resolve({"split_level": "deep"})
|
|
|
|
|
|
|
|
|
|
def test_non_boolean_menu_in_frontmatter(self):
|
|
|
|
|
with pytest.raises(ConfigError, match="menu must be a boolean"):
|
|
|
|
|
DeckConfig.resolve({"menu": "sometimes"})
|
Make `---` divide cards, and stop drawing ASCII rules
WML has no horizontal rule element -- its entire %layout entity is
`<br>` -- so a thematic break was being rendered as `<p>------------</p>`,
a hardcoded twelve-dash guess at screen width that wraps into nonsense on
a narrow device and is short on a wide one. It was the one construct
where the renderer invented a width out of nothing.
A `---` already looks like a divider and reads as one in every Markdown
document ever written, so it now is one: it starts a new card, by
default. Rules are never drawn, whether or not they divide.
Thematic breaks and `{.card Title}` markers are now a single mechanism --
an explicit divider, optionally carrying a title -- and compose freely in
one document. Both still win over --split-level. A section takes its
title from its own first heading when the divider does not supply one, so
the common shape needs no titles at all:
Intro on the menu.
---
## Weather
Cold and clear.
`--no-split-on-rule` / `split_on_rule: false` opts out of the splitting;
it does not bring the dashes back.
Three edges this opened, each fixed here rather than left to bite:
- Setext headings. `Heading` over `---` is an H2 in Markdown, but the
parser was ATX-only, so it produced a paragraph plus a rule. Once a
rule divides cards, a setext document would have split at every heading
and stranded each heading as body copy on the card before it. Setext
headings are now parsed, so such a document keeps its structure.
- Empty sections. A trailing `---`, or two in a row, produced an empty
"Untitled" card and a menu entry leading to it. Sections with no
renderable content are dropped.
- The multi-card threshold was two sections, so a document with a single
divider collapsed back into one card. Any explicit divider now makes a
multi-card deck: `A --- B` asks for two screens.
Also fixes a latent frontmatter bug this made far more likely: a document
opening with `---` and no `key: value` lines had its opening swallowed as
if the break were a frontmatter fence. A fenced block with no keys in it
is not frontmatter.
222 tests. Rendering examples/trail.md still matches md2txt's committed
output byte for byte; no golden file contains an ASCII rule any more.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-23 09:27:49 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestSplitOnRule:
|
|
|
|
|
def test_defaults_to_on(self):
|
|
|
|
|
assert DeckConfig.resolve().split_on_rule is True
|
|
|
|
|
|
|
|
|
|
def test_frontmatter_can_disable(self):
|
|
|
|
|
assert DeckConfig.resolve({"split_on_rule": "false"}).split_on_rule is False
|
|
|
|
|
|
|
|
|
|
def test_flag_overrides_frontmatter(self):
|
|
|
|
|
config = DeckConfig.resolve({"split_on_rule": "true"}, {"split_on_rule": False})
|
|
|
|
|
assert config.split_on_rule is False
|