Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 29 additions & 0 deletions crates/tree-sitter-qmd/tree-sitter-markdown/grammar.js
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,34 @@ const PANDOC_VALID_SYMBOLS =

const PANDOC_ALPHA_NUM = "0-9A-Za-z\\p{L}\\p{N}";
const PANDOC_PUNCTUATION = "\\p{Pd}#%&()/:+\\u{2026}";

// Po (Other Punctuation) and Pc (Connector Punctuation), NON-ASCII only.
// Pandoc folds these into the surrounding `Str` (e.g. `§`, `¶`, `·`, `†`,
// `‡`, `•`, `‣`, `‰`). The grammar previously enumerated the symbol
// categories (`Sm`/`Sk`/`So`/`Sc`) and dash punctuation (`\p{Pd}`) but not
// these, so a bare `Po` char in prose produced a parse ERROR (bd-6kewx).
// ASCII chars in these categories are excluded (codepoints >= U+0080) because
// they are either already handled above or reserved as qmd inline delimiters
// (`* _ ~ ^ ' " @ \` etc.). Generated by scripts/unicode-ranges.py.
const PANDOC_VALID_OTHER_PUNCTUATION =
"\\u{00A1}\\u{00A7}\\u{00B6}-\\u{00B7}\\u{00BF}\\u{037E}\\u{0387}\\u{055A}-\\u{055F}\\u{0589}\\u{05C0}\\u{05C3}"
+ "\\u{05C6}\\u{05F3}-\\u{05F4}\\u{0609}-\\u{060A}\\u{060C}-\\u{060D}\\u{061B}\\u{061E}-\\u{061F}\\u{066A}-\\u{066D}\\u{06D4}\\u{0700}-\\u{070D}\\u{07F7}-\\u{07F9}"
+ "\\u{0830}-\\u{083E}\\u{085E}\\u{0964}-\\u{0965}\\u{0970}\\u{09FD}\\u{0A76}\\u{0AF0}\\u{0C77}\\u{0C84}\\u{0DF4}"
+ "\\u{0E4F}\\u{0E5A}-\\u{0E5B}\\u{0F04}-\\u{0F12}\\u{0F14}\\u{0F85}\\u{0FD0}-\\u{0FD4}\\u{0FD9}-\\u{0FDA}\\u{104A}-\\u{104F}\\u{10FB}\\u{1360}-\\u{1368}"
+ "\\u{166E}\\u{16EB}-\\u{16ED}\\u{1735}-\\u{1736}\\u{17D4}-\\u{17D6}\\u{17D8}-\\u{17DA}\\u{1800}-\\u{1805}\\u{1807}-\\u{180A}\\u{1944}-\\u{1945}\\u{1A1E}-\\u{1A1F}\\u{1AA0}-\\u{1AA6}"
+ "\\u{1AA8}-\\u{1AAD}\\u{1B5A}-\\u{1B60}\\u{1BFC}-\\u{1BFF}\\u{1C3B}-\\u{1C3F}\\u{1C7E}-\\u{1C7F}\\u{1CC0}-\\u{1CC7}\\u{1CD3}\\u{2016}-\\u{2017}\\u{2020}-\\u{2027}\\u{2030}-\\u{2038}"
+ "\\u{203B}-\\u{203E}\\u{2041}-\\u{2043}\\u{2047}-\\u{2051}\\u{2053}\\u{2055}-\\u{205E}\\u{2CF9}-\\u{2CFC}\\u{2CFE}-\\u{2CFF}\\u{2D70}\\u{2E00}-\\u{2E01}\\u{2E06}-\\u{2E08}"
+ "\\u{2E0B}\\u{2E0E}-\\u{2E16}\\u{2E18}-\\u{2E19}\\u{2E1B}\\u{2E1E}-\\u{2E1F}\\u{2E2A}-\\u{2E2E}\\u{2E30}-\\u{2E39}\\u{2E3C}-\\u{2E3F}\\u{2E41}\\u{2E43}-\\u{2E4F}"
+ "\\u{2E52}\\u{3001}-\\u{3003}\\u{303D}\\u{30FB}\\u{A4FE}-\\u{A4FF}\\u{A60D}-\\u{A60F}\\u{A673}\\u{A67E}\\u{A6F2}-\\u{A6F7}\\u{A874}-\\u{A877}"
+ "\\u{A8CE}-\\u{A8CF}\\u{A8F8}-\\u{A8FA}\\u{A8FC}\\u{A92E}-\\u{A92F}\\u{A95F}\\u{A9C1}-\\u{A9CD}\\u{A9DE}-\\u{A9DF}\\u{AA5C}-\\u{AA5F}\\u{AADE}-\\u{AADF}\\u{AAF0}-\\u{AAF1}"
+ "\\u{ABEB}\\u{FE10}-\\u{FE16}\\u{FE19}\\u{FE30}\\u{FE45}-\\u{FE46}\\u{FE49}-\\u{FE4C}\\u{FE50}-\\u{FE52}\\u{FE54}-\\u{FE57}\\u{FE5F}-\\u{FE61}\\u{FE68}"
+ "\\u{FE6A}-\\u{FE6B}\\u{FF01}-\\u{FF03}\\u{FF05}-\\u{FF07}\\u{FF0A}\\u{FF0C}\\u{FF0E}-\\u{FF0F}\\u{FF1A}-\\u{FF1B}\\u{FF1F}-\\u{FF20}\\u{FF3C}\\u{FF61}"
+ "\\u{FF64}-\\u{FF65}\\u{10100}-\\u{10102}\\u{1039F}\\u{103D0}\\u{1056F}\\u{10857}\\u{1091F}\\u{1093F}\\u{10A50}-\\u{10A58}\\u{10A7F}"
+ "\\u{10AF0}-\\u{10AF6}\\u{10B39}-\\u{10B3F}\\u{10B99}-\\u{10B9C}\\u{10F55}-\\u{10F59}\\u{11047}-\\u{1104D}\\u{110BB}-\\u{110BC}\\u{110BE}-\\u{110C1}\\u{11140}-\\u{11143}\\u{11174}-\\u{11175}\\u{111C5}-\\u{111C8}"
+ "\\u{111CD}\\u{111DB}\\u{111DD}-\\u{111DF}\\u{11238}-\\u{1123D}\\u{112A9}\\u{1144B}-\\u{1144F}\\u{1145A}-\\u{1145B}\\u{1145D}\\u{114C6}\\u{115C1}-\\u{115D7}"
+ "\\u{11641}-\\u{11643}\\u{11660}-\\u{1166C}\\u{1173C}-\\u{1173E}\\u{1183B}\\u{11944}-\\u{11946}\\u{119E2}\\u{11A3F}-\\u{11A46}\\u{11A9A}-\\u{11A9C}\\u{11A9E}-\\u{11AA2}\\u{11C41}-\\u{11C45}"
+ "\\u{11C70}-\\u{11C71}\\u{11EF7}-\\u{11EF8}\\u{11FFF}\\u{12470}-\\u{12474}\\u{16A6E}-\\u{16A6F}\\u{16AF5}\\u{16B37}-\\u{16B3B}\\u{16B44}\\u{16E97}-\\u{16E9A}\\u{16FE2}"
+ "\\u{1BC9F}\\u{1DA87}-\\u{1DA8B}\\u{1E95E}-\\u{1E95F}\\u{203F}-\\u{2040}\\u{2054}\\u{FE33}-\\u{FE34}\\u{FE4D}-\\u{FE4F}\\u{FF3F}";
// Smart quotes that are allowed in pandoc_str
// U+2018 = ' (left single quotation mark)
// U+2019 = ' (right single quotation mark / apostrophe)
Expand Down Expand Up @@ -83,6 +111,7 @@ const PANDOC_REGEX_STR =
KEYCAP_EMOJI_REGEX,
EMOJI_REGEX,
"[" + PANDOC_PUNCTUATION + "]",
"[" + PANDOC_VALID_OTHER_PUNCTUATION + "]",
"[" + PANDOC_VALID_SYMBOLS + "]",
"[>.,;!?]",
startStrRegex +
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -94,4 +94,17 @@ def generate_ranges_excluding(category, exclude_codes):
print("\n" + "=" * 60)
print("So (Other Symbol) - no exclusions")
print("=" * 60)
so_result = generate_ranges_excluding('So', [])
so_result = generate_ranges_excluding('So', [])

# bd-6kewx: Po (Other Punctuation) and Pc (Connector Punctuation),
# NON-ASCII only. Pandoc folds these into Str; the grammar previously
# omitted them, so a bare § / ¶ / • etc. in prose produced a parse ERROR.
# ASCII chars in these categories are excluded because they are either
# already handled or reserved as qmd inline delimiters (* _ ~ ^ ' " @ \).
for cat in ('Po', 'Pc'):
print("\n" + "=" * 60)
print(f"{cat} (non-ASCII, codepoints >= U+0080) - for PANDOC_VALID_OTHER_PUNCTUATION")
print("=" * 60)
ascii_in_cat = [c for c in range(0x80)
if unicodedata.category(chr(c)) == cat]
generate_ranges_excluding(cat, ascii_in_cat)
Original file line number Diff line number Diff line change
Expand Up @@ -3598,7 +3598,7 @@
"members": [
{
"type": "PATTERN",
"value": "(?:\\\\.|([0-9#]\\uFE0F?\\u20E3)|(\\p{Extended_Pictographic}(\\p{Emoji_Modifier}|️)?(‍\\p{Extended_Pictographic}(\\p{Emoji_Modifier}|️)?)*)|[\\p{Pd}#%&()/:+\\u{2026}]|[+=¬±×÷϶؆-؈⁄⁒⁺-⁼₊-₌℘⅀-⅄⅋←-↔↚-↛↠↣↦↮⇎-⇏⇒⇔⇴-⋿⌠-⌡⍼⎛-⎳⏜-⏡▷◁◸-◿♯⟀-⟄⟇-⟥⟰-⟿⤀-⦂⦙-⧗⧜-⧻⧾-⫿⬰-⭄⭇-⭌﬩﹢﹤-﹦+<->|~¬←-↓𝛁𝛛𝛻𝜕𝜵𝝏𝝯𝞉𝞩𝟃𞻰-𞻱¨¯´¸˂-˅˒-˟˥-˫˭˯-˿͵΄-΅࢈᾽᾿-῁῍-῏῝-῟῭-`´-῾゛-゜꜀-꜖꜠-꜡꞉-꞊꭛꭪-꭫﮲-﯂^` ̄🏻-🏿\\p{So}¢£¤¥֏؋߾߿৲৳৻૱௹฿៛₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₱₲₳₴₵₶₷₸₹₺₻₼₽₾₿⃀꠸﷼﹩$¢£¥₩𑿝𑿞𑿟𑿠𞋿𞲰]|[>.,;!?]|(?:[\\u{00A0}\\u{1680}\\u{2000}-\\u{200A}\\u{2028}\\u{2029}\\u{202F}\\u{205F}\\u{3000}0-9A-Za-z\\p{L}\\p{N}\\u{2018}\\u{2019}\\u{201A}\\u{201B}\\u{201C}\\u{201D}\\u{201E}\\u{201F}\\u{2039}\\u{203A}\\u{00AB}\\u{00BB}-])(?:[!,.;?\\u{00A0}\\u{1680}\\u{2000}-\\u{200A}\\u{2028}\\u{2029}\\u{202F}\\u{205F}\\u{3000}0-9A-Za-z\\p{L}\\p{N}\\u{2018}\\u{2019}\\u{201A}\\u{201B}\\u{201C}\\u{201D}\\u{201E}\\u{201F}\\u{2039}\\u{203A}\\u{00AB}\\u{00BB}-]|['\\u{2018}\\u{2019}][\\p{L}\\p{N}]|(?:[_][0-9A-Za-z\\p{L}\\p{N}]))*)",
"value": "(?:\\\\.|([0-9#]\\uFE0F?\\u20E3)|(\\p{Extended_Pictographic}(\\p{Emoji_Modifier}|️)?(‍\\p{Extended_Pictographic}(\\p{Emoji_Modifier}|️)?)*)|[\\p{Pd}#%&()/:+\\u{2026}]|[\\u{00A1}\\u{00A7}\\u{00B6}-\\u{00B7}\\u{00BF}\\u{037E}\\u{0387}\\u{055A}-\\u{055F}\\u{0589}\\u{05C0}\\u{05C3}\\u{05C6}\\u{05F3}-\\u{05F4}\\u{0609}-\\u{060A}\\u{060C}-\\u{060D}\\u{061B}\\u{061E}-\\u{061F}\\u{066A}-\\u{066D}\\u{06D4}\\u{0700}-\\u{070D}\\u{07F7}-\\u{07F9}\\u{0830}-\\u{083E}\\u{085E}\\u{0964}-\\u{0965}\\u{0970}\\u{09FD}\\u{0A76}\\u{0AF0}\\u{0C77}\\u{0C84}\\u{0DF4}\\u{0E4F}\\u{0E5A}-\\u{0E5B}\\u{0F04}-\\u{0F12}\\u{0F14}\\u{0F85}\\u{0FD0}-\\u{0FD4}\\u{0FD9}-\\u{0FDA}\\u{104A}-\\u{104F}\\u{10FB}\\u{1360}-\\u{1368}\\u{166E}\\u{16EB}-\\u{16ED}\\u{1735}-\\u{1736}\\u{17D4}-\\u{17D6}\\u{17D8}-\\u{17DA}\\u{1800}-\\u{1805}\\u{1807}-\\u{180A}\\u{1944}-\\u{1945}\\u{1A1E}-\\u{1A1F}\\u{1AA0}-\\u{1AA6}\\u{1AA8}-\\u{1AAD}\\u{1B5A}-\\u{1B60}\\u{1BFC}-\\u{1BFF}\\u{1C3B}-\\u{1C3F}\\u{1C7E}-\\u{1C7F}\\u{1CC0}-\\u{1CC7}\\u{1CD3}\\u{2016}-\\u{2017}\\u{2020}-\\u{2027}\\u{2030}-\\u{2038}\\u{203B}-\\u{203E}\\u{2041}-\\u{2043}\\u{2047}-\\u{2051}\\u{2053}\\u{2055}-\\u{205E}\\u{2CF9}-\\u{2CFC}\\u{2CFE}-\\u{2CFF}\\u{2D70}\\u{2E00}-\\u{2E01}\\u{2E06}-\\u{2E08}\\u{2E0B}\\u{2E0E}-\\u{2E16}\\u{2E18}-\\u{2E19}\\u{2E1B}\\u{2E1E}-\\u{2E1F}\\u{2E2A}-\\u{2E2E}\\u{2E30}-\\u{2E39}\\u{2E3C}-\\u{2E3F}\\u{2E41}\\u{2E43}-\\u{2E4F}\\u{2E52}\\u{3001}-\\u{3003}\\u{303D}\\u{30FB}\\u{A4FE}-\\u{A4FF}\\u{A60D}-\\u{A60F}\\u{A673}\\u{A67E}\\u{A6F2}-\\u{A6F7}\\u{A874}-\\u{A877}\\u{A8CE}-\\u{A8CF}\\u{A8F8}-\\u{A8FA}\\u{A8FC}\\u{A92E}-\\u{A92F}\\u{A95F}\\u{A9C1}-\\u{A9CD}\\u{A9DE}-\\u{A9DF}\\u{AA5C}-\\u{AA5F}\\u{AADE}-\\u{AADF}\\u{AAF0}-\\u{AAF1}\\u{ABEB}\\u{FE10}-\\u{FE16}\\u{FE19}\\u{FE30}\\u{FE45}-\\u{FE46}\\u{FE49}-\\u{FE4C}\\u{FE50}-\\u{FE52}\\u{FE54}-\\u{FE57}\\u{FE5F}-\\u{FE61}\\u{FE68}\\u{FE6A}-\\u{FE6B}\\u{FF01}-\\u{FF03}\\u{FF05}-\\u{FF07}\\u{FF0A}\\u{FF0C}\\u{FF0E}-\\u{FF0F}\\u{FF1A}-\\u{FF1B}\\u{FF1F}-\\u{FF20}\\u{FF3C}\\u{FF61}\\u{FF64}-\\u{FF65}\\u{10100}-\\u{10102}\\u{1039F}\\u{103D0}\\u{1056F}\\u{10857}\\u{1091F}\\u{1093F}\\u{10A50}-\\u{10A58}\\u{10A7F}\\u{10AF0}-\\u{10AF6}\\u{10B39}-\\u{10B3F}\\u{10B99}-\\u{10B9C}\\u{10F55}-\\u{10F59}\\u{11047}-\\u{1104D}\\u{110BB}-\\u{110BC}\\u{110BE}-\\u{110C1}\\u{11140}-\\u{11143}\\u{11174}-\\u{11175}\\u{111C5}-\\u{111C8}\\u{111CD}\\u{111DB}\\u{111DD}-\\u{111DF}\\u{11238}-\\u{1123D}\\u{112A9}\\u{1144B}-\\u{1144F}\\u{1145A}-\\u{1145B}\\u{1145D}\\u{114C6}\\u{115C1}-\\u{115D7}\\u{11641}-\\u{11643}\\u{11660}-\\u{1166C}\\u{1173C}-\\u{1173E}\\u{1183B}\\u{11944}-\\u{11946}\\u{119E2}\\u{11A3F}-\\u{11A46}\\u{11A9A}-\\u{11A9C}\\u{11A9E}-\\u{11AA2}\\u{11C41}-\\u{11C45}\\u{11C70}-\\u{11C71}\\u{11EF7}-\\u{11EF8}\\u{11FFF}\\u{12470}-\\u{12474}\\u{16A6E}-\\u{16A6F}\\u{16AF5}\\u{16B37}-\\u{16B3B}\\u{16B44}\\u{16E97}-\\u{16E9A}\\u{16FE2}\\u{1BC9F}\\u{1DA87}-\\u{1DA8B}\\u{1E95E}-\\u{1E95F}\\u{203F}-\\u{2040}\\u{2054}\\u{FE33}-\\u{FE34}\\u{FE4D}-\\u{FE4F}\\u{FF3F}]|[+=¬±×÷϶؆-؈⁄⁒⁺-⁼₊-₌℘⅀-⅄⅋←-↔↚-↛↠↣↦↮⇎-⇏⇒⇔⇴-⋿⌠-⌡⍼⎛-⎳⏜-⏡▷◁◸-◿♯⟀-⟄⟇-⟥⟰-⟿⤀-⦂⦙-⧗⧜-⧻⧾-⫿⬰-⭄⭇-⭌﬩﹢﹤-﹦+<->|~¬←-↓𝛁𝛛𝛻𝜕𝜵𝝏𝝯𝞉𝞩𝟃𞻰-𞻱¨¯´¸˂-˅˒-˟˥-˫˭˯-˿͵΄-΅࢈᾽᾿-῁῍-῏῝-῟῭-`´-῾゛-゜꜀-꜖꜠-꜡꞉-꞊꭛꭪-꭫﮲-﯂^` ̄🏻-🏿\\p{So}¢£¤¥֏؋߾߿৲৳৻૱௹฿៛₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₱₲₳₴₵₶₷₸₹₺₻₼₽₾₿⃀꠸﷼﹩$¢£¥₩𑿝𑿞𑿟𑿠𞋿𞲰]|[>.,;!?]|(?:[\\u{00A0}\\u{1680}\\u{2000}-\\u{200A}\\u{2028}\\u{2029}\\u{202F}\\u{205F}\\u{3000}0-9A-Za-z\\p{L}\\p{N}\\u{2018}\\u{2019}\\u{201A}\\u{201B}\\u{201C}\\u{201D}\\u{201E}\\u{201F}\\u{2039}\\u{203A}\\u{00AB}\\u{00BB}-])(?:[!,.;?\\u{00A0}\\u{1680}\\u{2000}-\\u{200A}\\u{2028}\\u{2029}\\u{202F}\\u{205F}\\u{3000}0-9A-Za-z\\p{L}\\p{N}\\u{2018}\\u{2019}\\u{201A}\\u{201B}\\u{201C}\\u{201D}\\u{201E}\\u{201F}\\u{2039}\\u{203A}\\u{00AB}\\u{00BB}-]|['\\u{2018}\\u{2019}][\\p{L}\\p{N}]|(?:[_][0-9A-Za-z\\p{L}\\p{N}]))*)",
"flags": "u"
},
{
Expand Down
Loading