951a3000e6
* Fix four bugs surfaced by the commonmark-app example
- regex: bounded quantifiers {n,m} no longer expand exponentially. The
desugaring inlined the continuation per optional level, doubling it each
time, so {0,61} built a PEG the compiler expanded to ~2^61 nodes and hung.
Each level is now its own grammar rule referenced by name (jolt-3xur).
- strings are a seqable of chars for vec/set/into, matching seq. They went
through realize-for-iteration, which had no string case, so into/set got
raw bytes (code points) and set threw; vec used string/from-bytes (1-char
strings). realize-for-iteration now maps make-char over the bytes, and
core-vec matches (jolt-dl4s).
- clojure.string/split takes Java Pattern.split limit semantics: negative
keeps trailing empties, 0/omitted drops them (a no-match result stays
[input]), positive caps the part count with the remainder unsplit. It used
to delegate the limit to take, so a negative limit returned [] and the
2-arg form never trimmed trailing empties (jolt-ik3a).
- System/exit is registered (maps to os/exit), so (System/exit n) works
(jolt-w2wf).
* regex: single-digit backreferences \1..\9 (jolt-xtss)
\1..\9 now match the text captured by the corresponding group, so
patterns like ([-*_])\1\1 or (\w+) \1 work. The parser records which
groups are referenced; a referenced group additionally captures its text
under a tag and the backref compiles to a PEG (backmatch). Only referenced
groups change — they match possessively (the CPS-over-possessive-PEG engine
can't backtrack into a tagged capture), so backtracking back into a
backreferenced group isn't supported (rare). Unreferenced groups keep full
backtracking and position-based result capture unchanged.
---------
Co-authored-by: Yogthos <yogthos@gmail.com>
88 lines
6 KiB
Text
88 lines
6 KiB
Text
# Specification: strings (str + clojure.string).
|
|
(use ../support/harness)
|
|
|
|
(defspec "string / str & basics"
|
|
["str concat" "\"abc\"" "(str \"a\" \"b\" \"c\")"]
|
|
["str of numbers" "\"12\"" "(str 1 2)"]
|
|
["str nil is empty" "\"\"" "(str nil)"]
|
|
["str mixed" "\"a1:b\"" "(str \"a\" 1 :b)"]
|
|
["str of coll" "\"[1 2]\"" "(str [1 2])"]
|
|
["count" "3" "(count \"abc\")"]
|
|
["subs from" "\"bc\"" "(subs \"abc\" 1)"]
|
|
["subs range" "\"b\"" "(subs \"abc\" 1 2)"]
|
|
["string? true" "true" "(string? \"x\")"]
|
|
["pr-str vector" "\"[1 2 3]\"" "(pr-str [1 2 3])"]
|
|
["pr-str quotes str" "\"\\\"hi\\\"\"" "(pr-str \"hi\")"]
|
|
# a var's :meta/:ns refs are cyclic — pr-str/str render it as #'ns/name
|
|
# rather than recursing into (and looping on) the var's fields.
|
|
["pr-str of a var" "\"#'user/vv\"" "(pr-str (def vv 1))"]
|
|
["str of a var" "\"#'user/ww\"" "(str (def ww 2))"]
|
|
["pr-str of a defn" "\"#'user/gg\"" "(pr-str (defn gg [x] x))"]
|
|
["seq of string" "[\\a \\b]" "(seq \"ab\")"])
|
|
|
|
(defspec "string as a seqable of chars (jolt-dl4s)"
|
|
["vec of string" "[\\a \\b]" "(vec \"ab\")"]
|
|
["into [] of string" "[\\a \\b]" "(into [] \"ab\")"]
|
|
["set of string" "true" "(= #{\\a \\b} (set \"ab\"))"]
|
|
["into #{} of string" "true" "(= #{\\a \\b} (into #{} \"ab\"))"]
|
|
["set dedups chars" "2" "(count (set \"aab\"))"]
|
|
["mapv over string" "[\\a \\b]" "(mapv identity \"ab\")"])
|
|
|
|
(defspec "clojure.string / split limit (jolt-ik3a)"
|
|
["neg keeps trailing" "[\"a\" \"\" \"\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,,\" #\",\" -1))"]
|
|
["zero trims trailing" "[\"a\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,,\" #\",\" 0))"]
|
|
["omitted trims" "[\"a\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,,\" #\",\"))"]
|
|
["positive caps parts" "[\"a\" \"b,c\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,b,c\" #\",\" 2))"]
|
|
["empty string" "[\"\"]" "(do (require (quote [clojure.string :as s])) (s/split \"\" #\",\"))"]
|
|
["interior empties kept" "[\"a\" \"\" \"b\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,,b\" #\",\"))"])
|
|
|
|
(defspec "clojure.string"
|
|
["join" "\"a,b,c\"" "(do (require (quote [clojure.string :as s])) (s/join \",\" [\"a\" \"b\" \"c\"]))"]
|
|
["join no sep" "\"abc\"" "(do (require (quote [clojure.string :as s])) (s/join [\"a\" \"b\" \"c\"]))"]
|
|
["split" "[\"a\" \"b\"]" "(do (require (quote [clojure.string :as s])) (s/split \"a,b\" #\",\"))"]
|
|
["split-lines" "[\"a\" \"b\"]" "(do (require (quote [clojure.string :as s])) (s/split-lines \"a\\nb\"))"]
|
|
["upper-case" "\"ABC\"" "(do (require (quote [clojure.string :as s])) (s/upper-case \"abc\"))"]
|
|
["lower-case" "\"abc\"" "(do (require (quote [clojure.string :as s])) (s/lower-case \"ABC\"))"]
|
|
["capitalize" "\"Abc\"" "(do (require (quote [clojure.string :as s])) (s/capitalize \"abc\"))"]
|
|
["trim" "\"x\"" "(do (require (quote [clojure.string :as s])) (s/trim \" x \"))"]
|
|
["triml" "\"x \"" "(do (require (quote [clojure.string :as s])) (s/triml \" x \"))"]
|
|
["blank? true" "true" "(do (require (quote [clojure.string :as s])) (s/blank? \" \"))"]
|
|
["blank? false" "false" "(do (require (quote [clojure.string :as s])) (s/blank? \"x\"))"]
|
|
["includes?" "true" "(do (require (quote [clojure.string :as s])) (s/includes? \"hello\" \"ell\"))"]
|
|
["starts-with?" "true" "(do (require (quote [clojure.string :as s])) (s/starts-with? \"hello\" \"he\"))"]
|
|
["ends-with?" "true" "(do (require (quote [clojure.string :as s])) (s/ends-with? \"hello\" \"lo\"))"]
|
|
["replace" "\"hexxo\"" "(do (require (quote [clojure.string :as s])) (s/replace \"hello\" \"l\" \"x\"))"]
|
|
["reverse" "\"cba\"" "(do (require (quote [clojure.string :as s])) (s/reverse \"abc\"))"]
|
|
["index-of" "2" "(do (require (quote [clojure.string :as s])) (s/index-of \"hello\" \"l\"))"])
|
|
|
|
# subs validates bounds like Clojure (no Janet from-end/clamping).
|
|
(defspec "string / subs strictness"
|
|
["subs basic" "\"bcd\"" "(subs \"abcde\" 1 4)"]
|
|
["subs to end" "\"cde\"" "(subs \"abcde\" 2)"]
|
|
["subs start>end" :throws "(subs \"abcde\" 2 1)"]
|
|
["subs negative" :throws "(subs \"abcde\" -1)"]
|
|
["subs end past len" :throws "(subs \"abcde\" 1 6)"]
|
|
["subs nil start" :throws "(subs \"abcde\" nil 2)"]
|
|
["subs on nil" :throws "(subs nil 1 2)"])
|
|
|
|
(defspec "string / namespace-munge"
|
|
["hyphens to underscores" "\"a_b_c\"" "(namespace-munge \"a-b-c\")"]
|
|
["from a symbol" "\"foo_bar\"" "(namespace-munge (quote foo-bar))"]
|
|
["no hyphens unchanged" "\"ok\"" "(namespace-munge \"ok\")"])
|
|
|
|
# (get s i) indexes a string and returns the char, like Clojure (nth already
|
|
# did; get did not — reitit's path parser relies on it).
|
|
(defspec "strings / get indexes a string"
|
|
["get returns the char" "true" "(= (get \"a:b\" 1) \\:)"]
|
|
["get first char" "\\a" "(get \"abc\" 0)"]
|
|
["get out of range nil" "nil" "(get \"abc\" 9)"]
|
|
["get negative nil" "nil" "(get \"abc\" -1)"]
|
|
["get default honored" ":none" "(get \"abc\" 9 :none)"])
|
|
|
|
# clojure.string/trim-newline (ported from clojure.string): strips trailing \n/\r.
|
|
(defspec "clojure.string / trim-newline"
|
|
["trailing newline" "\"x\"" "(do (require (quote [clojure.string :as s])) (s/trim-newline \"x\\n\"))"]
|
|
["trailing \\r\\n" "\"x\"" "(do (require (quote [clojure.string :as s])) (s/trim-newline \"x\\r\\n\"))"]
|
|
["no trailing" "\"ab\"" "(do (require (quote [clojure.string :as s])) (s/trim-newline \"ab\"))"]
|
|
["only newlines" "\"\"" "(do (require (quote [clojure.string :as s])) (s/trim-newline \"\\n\\n\"))"]
|
|
["interior kept" "\"a\\nb\"" "(do (require (quote [clojure.string :as s])) (s/trim-newline \"a\\nb\\n\"))"])
|