giles
a11d0941e9
Generator changes (tests/playwright/generate-sx-tests.py):
- toHaveCSS regex: balance parens so `'rgb(255, 0, 0)'` is captured intact
(was truncating at first `)`)
- Map browser-computed colors `rgb(R,G,B)` back to CSS keywords
(red/green/blue/black/white) — our DOM mock returns the inline value
- js_val_to_sx now handles object literals `{a: 1, b: {c: 2}}` → `{:a 1 :b {:c 2}}`
- Pattern 2 (`var x = await run(...)`) now captures locals via balanced-brace
scan and emits `eval-hs-locals` instead of `eval-hs`
- Pattern 1 with locals: emit `eval-hs-locals` (was wrapping in `let`, which
doesn't reach the inner HS env)
- Stop collapsing `\"` → `"` in raw HTML (line 218): the backslash escapes
are legitimate in single-quoted `_='...'` HS attribute values containing
nested HS scripts
Test-framework changes (regenerated into spec/tests/test-hyperscript-behavioral.sx):
- `_hs-wrap-body`: returns expression value if non-nil, else `it`. Lets bare
expressions (`foo.foo`) and `it`-mutating scripts (`pick first 3 of arr;
set $test to it`) both round-trip through the same wrapper
- `eval-hs-locals` now injects locals via `(let ((name (quote val)) ...) sx)`
rather than `apply handler (cons nil vals)` — works around a JIT loop on
some compiled forms (e.g. `bar.doh of foo` with undefined `bar`)
Also synced lib/hyperscript/*.sx → shared/static/wasm/sx/hs-*.sx (the WASM
test runner reads from the wasm/sx/ copies).
Net per-cluster pass counts (vs prior baseline):
- put: 23 → 29 (+6)
- set: 21 → 28 (+7)
- show: 7 → 15 (+8)
- expressions/propertyAccess: 3 → 9 (+6)
- expressions/possessiveExpression: 17 → 18 (+1)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
623 lines
18 KiB
Plaintext
623 lines
18 KiB
Plaintext
;; _hyperscript tokenizer — produces token stream from hyperscript source
|
|
;;
|
|
;; Tokens: {:type T :value V :pos P}
|
|
;; Types: "keyword" "ident" "number" "string" "class" "id" "attr" "style"
|
|
;; "selector" "op" "dot" "paren-open" "paren-close" "bracket-open"
|
|
;; "bracket-close" "brace-open" "brace-close" "comma" "colon"
|
|
;; "template" "local" "eof"
|
|
|
|
;; ── Token constructor ─────────────────────────────────────────────
|
|
|
|
(define hs-make-token (fn (type value pos) {:pos pos :value value :type type}))
|
|
|
|
;; ── Character predicates ──────────────────────────────────────────
|
|
|
|
(define hs-digit? (fn (c) (and (>= c "0") (<= c "9"))))
|
|
|
|
(define
|
|
hs-letter?
|
|
(fn (c) (or (and (>= c "a") (<= c "z")) (and (>= c "A") (<= c "Z")))))
|
|
|
|
(define hs-ident-start? (fn (c) (or (hs-letter? c) (= c "_") (= c "$"))))
|
|
|
|
(define
|
|
hs-ident-char?
|
|
(fn
|
|
(c)
|
|
(or (hs-letter? c) (hs-digit? c) (= c "_") (= c "$") (= c "-"))))
|
|
|
|
(define hs-ws? (fn (c) (or (= c " ") (= c "\t") (= c "\n") (= c "\r"))))
|
|
|
|
;; ── Keyword set ───────────────────────────────────────────────────
|
|
|
|
(define
|
|
hs-keywords
|
|
(list
|
|
"on"
|
|
"end"
|
|
"set"
|
|
"to"
|
|
"put"
|
|
"into"
|
|
"before"
|
|
"after"
|
|
"add"
|
|
"remove"
|
|
"toggle"
|
|
"if"
|
|
"else"
|
|
"otherwise"
|
|
"then"
|
|
"from"
|
|
"in"
|
|
"of"
|
|
"for"
|
|
"until"
|
|
"wait"
|
|
"send"
|
|
"trigger"
|
|
"call"
|
|
"get"
|
|
"take"
|
|
"log"
|
|
"hide"
|
|
"show"
|
|
"repeat"
|
|
"while"
|
|
"times"
|
|
"forever"
|
|
"break"
|
|
"continue"
|
|
"return"
|
|
"throw"
|
|
"catch"
|
|
"finally"
|
|
"def"
|
|
"tell"
|
|
"make"
|
|
"fetch"
|
|
"as"
|
|
"with"
|
|
"every"
|
|
"or"
|
|
"and"
|
|
"not"
|
|
"is"
|
|
"no"
|
|
"the"
|
|
"my"
|
|
"me"
|
|
"it"
|
|
"its"
|
|
"result"
|
|
"true"
|
|
"false"
|
|
"null"
|
|
"when"
|
|
"between"
|
|
"at"
|
|
"by"
|
|
"queue"
|
|
"elsewhere"
|
|
"event"
|
|
"target"
|
|
"detail"
|
|
"sender"
|
|
"index"
|
|
"indexed"
|
|
"increment"
|
|
"decrement"
|
|
"append"
|
|
"settle"
|
|
"transition"
|
|
"over"
|
|
"closest"
|
|
"next"
|
|
"previous"
|
|
"first"
|
|
"last"
|
|
"random"
|
|
"pick"
|
|
"empty"
|
|
"clear"
|
|
"swap"
|
|
"open"
|
|
"close"
|
|
"exists"
|
|
"matches"
|
|
"contains"
|
|
"do"
|
|
"unless"
|
|
"you"
|
|
"your"
|
|
"new"
|
|
"init"
|
|
"start"
|
|
"go"
|
|
"js"
|
|
"less"
|
|
"than"
|
|
"greater"
|
|
"class"
|
|
"anything"
|
|
"install"
|
|
"measure"
|
|
"behavior"
|
|
"called"
|
|
"render"
|
|
"eval"
|
|
"I"
|
|
"am"
|
|
"does"
|
|
"some"
|
|
"mod"
|
|
"equal"
|
|
"equals"
|
|
"really"
|
|
"include"
|
|
"includes"
|
|
"contain"
|
|
"undefined"
|
|
"exist"
|
|
"match"
|
|
"beep"
|
|
"where"
|
|
"sorted"
|
|
"mapped"
|
|
"split"
|
|
"joined"
|
|
"descending"
|
|
"ascending"
|
|
"scroll"
|
|
"select"
|
|
"reset"
|
|
"default"
|
|
"halt"
|
|
"precedes"
|
|
"precede"
|
|
"follow"
|
|
"follows"
|
|
"ignoring"
|
|
"case"
|
|
"changes"
|
|
"focus"
|
|
"blur"
|
|
"dom"
|
|
"morph"
|
|
"using"))
|
|
|
|
(define hs-keyword? (fn (word) (some (fn (k) (= k word)) hs-keywords)))
|
|
|
|
;; ── Main tokenizer ────────────────────────────────────────────────
|
|
|
|
(define
|
|
hs-tokenize
|
|
(fn
|
|
(src)
|
|
(let
|
|
((tokens (list)) (pos 0) (src-len (len src)))
|
|
(define
|
|
hs-peek
|
|
(fn
|
|
(offset)
|
|
(if (< (+ pos offset) src-len) (nth src (+ pos offset)) nil)))
|
|
(define hs-cur (fn () (hs-peek 0)))
|
|
(define hs-advance! (fn (n) (set! pos (+ pos n))))
|
|
(define
|
|
skip-ws!
|
|
(fn
|
|
()
|
|
(when
|
|
(and (< pos src-len) (hs-ws? (hs-cur)))
|
|
(hs-advance! 1)
|
|
(skip-ws!))))
|
|
(define
|
|
skip-comment!
|
|
(fn
|
|
()
|
|
(when
|
|
(and (< pos src-len) (not (= (hs-cur) "\n")))
|
|
(hs-advance! 1)
|
|
(skip-comment!))))
|
|
(define
|
|
read-ident
|
|
(fn
|
|
(start)
|
|
(when
|
|
(and (< pos src-len) (hs-ident-char? (hs-cur)))
|
|
(hs-advance! 1)
|
|
(read-ident start))
|
|
(slice src start pos)))
|
|
(define
|
|
read-number
|
|
(fn
|
|
(start)
|
|
(when
|
|
(and (< pos src-len) (hs-digit? (hs-cur)))
|
|
(hs-advance! 1)
|
|
(read-number start))
|
|
(when
|
|
(and
|
|
(< pos src-len)
|
|
(= (hs-cur) ".")
|
|
(< (+ pos 1) src-len)
|
|
(hs-digit? (hs-peek 1)))
|
|
(hs-advance! 1)
|
|
(define
|
|
read-frac
|
|
(fn
|
|
()
|
|
(when
|
|
(and (< pos src-len) (hs-digit? (hs-cur)))
|
|
(hs-advance! 1)
|
|
(read-frac))))
|
|
(read-frac))
|
|
(do
|
|
(when
|
|
(and
|
|
(< pos src-len)
|
|
(or (= (hs-cur) "e") (= (hs-cur) "E"))
|
|
(or
|
|
(and (< (+ pos 1) src-len) (hs-digit? (hs-peek 1)))
|
|
(and
|
|
(< (+ pos 2) src-len)
|
|
(or (= (hs-peek 1) "+") (= (hs-peek 1) "-"))
|
|
(hs-digit? (hs-peek 2)))))
|
|
(hs-advance! 1)
|
|
(when
|
|
(and
|
|
(< pos src-len)
|
|
(or (= (hs-cur) "+") (= (hs-cur) "-")))
|
|
(hs-advance! 1))
|
|
(define
|
|
read-exp-digits
|
|
(fn
|
|
()
|
|
(when
|
|
(and (< pos src-len) (hs-digit? (hs-cur)))
|
|
(hs-advance! 1)
|
|
(read-exp-digits))))
|
|
(read-exp-digits))
|
|
(let
|
|
((num-end pos))
|
|
(when
|
|
(and
|
|
(< pos src-len)
|
|
(or (= (hs-cur) "m") (= (hs-cur) "s")))
|
|
(if
|
|
(and
|
|
(= (hs-cur) "m")
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) "s"))
|
|
(hs-advance! 2)
|
|
(when (= (hs-cur) "s") (hs-advance! 1))))
|
|
(slice src start pos)))))
|
|
(define
|
|
read-string
|
|
(fn
|
|
(quote-char)
|
|
(let
|
|
((chars (list)))
|
|
(hs-advance! 1)
|
|
(define
|
|
loop
|
|
(fn
|
|
()
|
|
(cond
|
|
(>= pos src-len)
|
|
nil
|
|
(= (hs-cur) "\\")
|
|
(do
|
|
(hs-advance! 1)
|
|
(when
|
|
(< pos src-len)
|
|
(let
|
|
((ch (hs-cur)))
|
|
(cond
|
|
(= ch "n")
|
|
(append! chars "\n")
|
|
(= ch "t")
|
|
(append! chars "\t")
|
|
(= ch "\\")
|
|
(append! chars "\\")
|
|
(= ch quote-char)
|
|
(append! chars quote-char)
|
|
:else (do (append! chars "\\") (append! chars ch)))
|
|
(hs-advance! 1)))
|
|
(loop))
|
|
(= (hs-cur) quote-char)
|
|
(hs-advance! 1)
|
|
:else (do (append! chars (hs-cur)) (hs-advance! 1) (loop)))))
|
|
(loop)
|
|
(join "" chars))))
|
|
(define
|
|
read-template
|
|
(fn
|
|
()
|
|
(let
|
|
((chars (list)))
|
|
(hs-advance! 1)
|
|
(define
|
|
loop
|
|
(fn
|
|
()
|
|
(cond
|
|
(>= pos src-len)
|
|
nil
|
|
(= (hs-cur) "`")
|
|
(hs-advance! 1)
|
|
(and
|
|
(= (hs-cur) "$")
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) "{"))
|
|
(do
|
|
(append! chars "${")
|
|
(hs-advance! 2)
|
|
(let
|
|
((depth 1))
|
|
(define
|
|
inner
|
|
(fn
|
|
()
|
|
(when
|
|
(and (< pos src-len) (> depth 0))
|
|
(cond
|
|
(= (hs-cur) "{")
|
|
(do
|
|
(set! depth (+ depth 1))
|
|
(append! chars (hs-cur))
|
|
(hs-advance! 1)
|
|
(inner))
|
|
(= (hs-cur) "}")
|
|
(do
|
|
(set! depth (- depth 1))
|
|
(when (> depth 0) (append! chars (hs-cur)))
|
|
(hs-advance! 1)
|
|
(when (> depth 0) (inner)))
|
|
:else (do
|
|
(append! chars (hs-cur))
|
|
(hs-advance! 1)
|
|
(inner))))))
|
|
(inner))
|
|
(append! chars "}")
|
|
(loop))
|
|
:else (do (append! chars (hs-cur)) (hs-advance! 1) (loop)))))
|
|
(loop)
|
|
(join "" chars))))
|
|
(define
|
|
read-selector
|
|
(fn
|
|
()
|
|
(let
|
|
((chars (list)))
|
|
(hs-advance! 1)
|
|
(define
|
|
loop
|
|
(fn
|
|
()
|
|
(cond
|
|
(>= pos src-len)
|
|
nil
|
|
(and
|
|
(= (hs-cur) "/")
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) ">"))
|
|
(hs-advance! 2)
|
|
:else (do (append! chars (hs-cur)) (hs-advance! 1) (loop)))))
|
|
(loop)
|
|
(join "" chars))))
|
|
(define
|
|
read-class-name
|
|
(fn
|
|
(start)
|
|
(when
|
|
(and
|
|
(< pos src-len)
|
|
(or
|
|
(hs-ident-char? (hs-cur))
|
|
(= (hs-cur) ":")
|
|
(= (hs-cur) "[")
|
|
(= (hs-cur) "]")))
|
|
(hs-advance! 1)
|
|
(read-class-name start))
|
|
(slice src start pos)))
|
|
(define
|
|
hs-emit!
|
|
(fn
|
|
(type value start)
|
|
(append! tokens (hs-make-token type value start))))
|
|
(define
|
|
scan!
|
|
(fn
|
|
()
|
|
(skip-ws!)
|
|
(when
|
|
(< pos src-len)
|
|
(let
|
|
((ch (hs-cur)) (start pos))
|
|
(cond
|
|
(and (= ch "-") (< (+ pos 1) src-len) (= (hs-peek 1) "-"))
|
|
(do (hs-advance! 2) (skip-comment!) (scan!))
|
|
(and (= ch "/") (< (+ pos 1) src-len) (= (hs-peek 1) "/"))
|
|
(do (hs-advance! 2) (skip-comment!) (scan!))
|
|
(and
|
|
(= ch "<")
|
|
(< (+ pos 1) src-len)
|
|
(not (= (hs-peek 1) "="))
|
|
(or
|
|
(hs-letter? (hs-peek 1))
|
|
(= (hs-peek 1) ".")
|
|
(= (hs-peek 1) "#")
|
|
(= (hs-peek 1) "[")
|
|
(= (hs-peek 1) "*")
|
|
(= (hs-peek 1) ":")))
|
|
(do (hs-emit! "selector" (read-selector) start) (scan!))
|
|
(and (= ch ".") (< (+ pos 1) src-len) (= (hs-peek 1) "."))
|
|
(do (hs-emit! "op" ".." start) (hs-advance! 2) (scan!))
|
|
(and
|
|
(= ch ".")
|
|
(< (+ pos 1) src-len)
|
|
(or
|
|
(hs-letter? (hs-peek 1))
|
|
(= (hs-peek 1) "-")
|
|
(= (hs-peek 1) "_")))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "class" (read-class-name pos) start)
|
|
(scan!))
|
|
(and
|
|
(= ch "#")
|
|
(< (+ pos 1) src-len)
|
|
(hs-ident-start? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "id" (read-ident pos) start)
|
|
(scan!))
|
|
(and
|
|
(= ch "@")
|
|
(< (+ pos 1) src-len)
|
|
(hs-ident-char? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "attr" (read-ident pos) start)
|
|
(scan!))
|
|
(and
|
|
(= ch "^")
|
|
(< (+ pos 1) src-len)
|
|
(hs-ident-char? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "hat" (read-ident pos) start)
|
|
(scan!))
|
|
(and
|
|
(= ch "~")
|
|
(< (+ pos 1) src-len)
|
|
(hs-letter? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "component" (str "~" (read-ident pos)) start)
|
|
(scan!))
|
|
(and
|
|
(= ch "*")
|
|
(< (+ pos 1) src-len)
|
|
(hs-letter? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "style" (read-ident pos) start)
|
|
(scan!))
|
|
(and
|
|
(= ch ":")
|
|
(< (+ pos 1) src-len)
|
|
(hs-ident-start? (hs-peek 1)))
|
|
(do
|
|
(hs-advance! 1)
|
|
(hs-emit! "local" (read-ident pos) start)
|
|
(scan!))
|
|
(or
|
|
(= ch "\"")
|
|
(and
|
|
(= ch "'")
|
|
(not
|
|
(and
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) "s")
|
|
(or
|
|
(>= (+ pos 2) src-len)
|
|
(not (hs-ident-char? (hs-peek 2))))))))
|
|
(do (hs-emit! "string" (read-string ch) start) (scan!))
|
|
(= ch "`")
|
|
(do (hs-emit! "template" (read-template) start) (scan!))
|
|
(hs-digit? ch)
|
|
(do (hs-emit! "number" (read-number start) start) (scan!))
|
|
(hs-ident-start? ch)
|
|
(do
|
|
(let
|
|
((word (read-ident start)))
|
|
(hs-emit!
|
|
(if (hs-keyword? word) "keyword" "ident")
|
|
word
|
|
start))
|
|
(scan!))
|
|
(and
|
|
(or (= ch "=") (= ch "!") (= ch "<") (= ch ">"))
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) "="))
|
|
(do
|
|
(if
|
|
(and
|
|
(or (= ch "=") (= ch "!"))
|
|
(< (+ pos 2) src-len)
|
|
(= (hs-peek 2) "="))
|
|
(do (hs-emit! "op" (str ch "==") start) (hs-advance! 3))
|
|
(do (hs-emit! "op" (str ch "=") start) (hs-advance! 2)))
|
|
(scan!))
|
|
(and
|
|
(= ch "'")
|
|
(< (+ pos 1) src-len)
|
|
(= (hs-peek 1) "s")
|
|
(or
|
|
(>= (+ pos 2) src-len)
|
|
(not (hs-ident-char? (hs-peek 2)))))
|
|
(do (hs-emit! "op" "'s" start) (hs-advance! 2) (scan!))
|
|
(= ch "(")
|
|
(do
|
|
(hs-emit! "paren-open" "(" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch ")")
|
|
(do
|
|
(hs-emit! "paren-close" ")" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch "[")
|
|
(do
|
|
(hs-emit! "bracket-open" "[" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch "]")
|
|
(do
|
|
(hs-emit! "bracket-close" "]" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch "{")
|
|
(do
|
|
(hs-emit! "brace-open" "{" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch "}")
|
|
(do
|
|
(hs-emit! "brace-close" "}" start)
|
|
(hs-advance! 1)
|
|
(scan!))
|
|
(= ch ",")
|
|
(do (hs-emit! "comma" "," start) (hs-advance! 1) (scan!))
|
|
(= ch "+")
|
|
(do (hs-emit! "op" "+" start) (hs-advance! 1) (scan!))
|
|
(= ch "-")
|
|
(do (hs-emit! "op" "-" start) (hs-advance! 1) (scan!))
|
|
(= ch "/")
|
|
(do (hs-emit! "op" "/" start) (hs-advance! 1) (scan!))
|
|
(= ch "=")
|
|
(do (hs-emit! "op" "=" start) (hs-advance! 1) (scan!))
|
|
(= ch "<")
|
|
(do (hs-emit! "op" "<" start) (hs-advance! 1) (scan!))
|
|
(= ch ">")
|
|
(do (hs-emit! "op" ">" start) (hs-advance! 1) (scan!))
|
|
(= ch "!")
|
|
(do (hs-emit! "op" "!" start) (hs-advance! 1) (scan!))
|
|
(= ch "*")
|
|
(do (hs-emit! "op" "*" start) (hs-advance! 1) (scan!))
|
|
(= ch "%")
|
|
(do (hs-emit! "op" "%" start) (hs-advance! 1) (scan!))
|
|
(= ch ".")
|
|
(do (hs-emit! "dot" "." start) (hs-advance! 1) (scan!))
|
|
(= ch "\\")
|
|
(do (hs-emit! "op" "\\" start) (hs-advance! 1) (scan!))
|
|
(= ch ":")
|
|
(do (hs-emit! "colon" ":" start) (hs-advance! 1) (scan!))
|
|
(= ch "|")
|
|
(do (hs-emit! "op" "|" start) (hs-advance! 1) (scan!))
|
|
:else (do (hs-advance! 1) (scan!)))))))
|
|
(scan!)
|
|
(hs-emit! "eof" nil pos)
|
|
tokens))) |