The three parsing primitives the TMX path needs that were not already in the tree (zlib inflate + the JSON reader already shipped): - Xml.* — a minimal, deterministic pure-Ludic XML reader for the element/attribute/CDATA subset TMX/TSX/TX use, spliced on demand. Handles nested elements, single/double-quoted attributes, text + <![CDATA[…]]>, comments, the <?xml?> prolog and <!DOCTYPE>, the five predefined entities and numeric character references. - Base64.* — standard base64 (RFC 4648) decode + a matching pure-Ludic encoder; the decoder ignores the whitespace Tiled wraps into <data>. Splicing Base64.* also pulls in inflate.ludic so a plain tool can run the full base64 -> zlib/gzip decode chain. - z_gunzip — gzip framing (RFC 1952) over the existing DEFLATE inflater: skip the 10-byte header + optional fields, inflate the body, ignore the CRC32/ISIZE trailer. Golden corpus vendored under assets/tiled-fixtures/ (mapeditor/tiled examples, attributed, + hand-authored multi-encoding fixtures). New example library/tiled_p0.ludic proves all three (21 assertions); docs pages + inventory added so check-impl stays green. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
87 lines
3.1 KiB
Text
87 lines
3.1 KiB
Text
# ============================================================================
|
|
# base64.ludic — standard base64 (RFC 4648) encode + decode, in Ludic (`Base64.*`).
|
|
#
|
|
# `Crypto.base64` already encodes (hand-written IR, tied to the crypto prelude);
|
|
# the Tiled data pipeline (issue #67) needs a *decoder* — base64 layer data feeds
|
|
# the DEFLATE inflater. This is that decoder, plus a matching pure-Ludic encoder
|
|
# so the namespace is self-contained and spliceable on its own (no crypto prelude
|
|
# dependency). Deterministic, allocation the only cost.
|
|
#
|
|
# ludicc splices this file when a program mentions `Base64.*` (parse.ludic). The
|
|
# decoder ignores ASCII whitespace (TMX embeds newlines/indentation in its base64
|
|
# `<data>`), and '=' padding ends the stream.
|
|
# ============================================================================
|
|
|
|
# the standard alphabet value of a base64 character, or -1 for anything else
|
|
# (whitespace, '=', stray bytes — the decoder skips them / stops on '=').
|
|
function b64_val(c: int) -> int {
|
|
if c >= 65 and c <= 90 { return c - 65 } # 'A'..'Z' -> 0..25
|
|
if c >= 97 and c <= 122 { return c - 71 } # 'a'..'z' -> 26..51
|
|
if c >= 48 and c <= 57 { return c + 4 } # '0'..'9' -> 52..61
|
|
if c == 43 { return 62 } # '+'
|
|
if c == 47 { return 63 } # '/'
|
|
return 0 - 1
|
|
}
|
|
|
|
# decode NUL-terminated base64 `src` into the caller's `out` buffer; returns the
|
|
# number of bytes written. Whitespace is ignored; '=' padding terminates. `out`
|
|
# must hold at least (len(src)*3)/4 bytes.
|
|
function b64_decode(src: pointer, out: pointer) -> int {
|
|
var acc = 0
|
|
var nbits = 0
|
|
var w = 0
|
|
var i = 0
|
|
var c = src[i]
|
|
while c != 0 {
|
|
if c == 61 { return w } # '=' -> done
|
|
let v = b64_val(c)
|
|
if v >= 0 {
|
|
acc = (acc << 6) | v
|
|
nbits = nbits + 6
|
|
if nbits >= 8 {
|
|
nbits = nbits - 8
|
|
out[w] = (acc >> nbits) & 255
|
|
w = w + 1
|
|
}
|
|
}
|
|
i = i + 1
|
|
c = src[i]
|
|
}
|
|
return w
|
|
}
|
|
|
|
# decode base64 text -> a fresh NUL-terminated string of the decoded bytes.
|
|
# (For binary payloads that may contain NUL, decode into a sized buffer with
|
|
# `b64_decode` and track the returned length instead.)
|
|
function base64_decode(src: pointer) -> pointer {
|
|
let cap = len(src) + 4
|
|
let out = bytes(cap)
|
|
let w = b64_decode(src, out)
|
|
out[w] = 0
|
|
return out
|
|
}
|
|
|
|
# encode the bytes of NUL-terminated `src` as standard base64 (with '=' padding).
|
|
function base64_encode(src: pointer) -> pointer {
|
|
let tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
|
|
let n = len(src)
|
|
var out = ""
|
|
var i = 0
|
|
while i < n {
|
|
let b0 = src[i]
|
|
var b1 = 0
|
|
var b2 = 0
|
|
var have = 1
|
|
if i + 1 < n { b1 = src[i + 1]; have = 2 }
|
|
if i + 2 < n { b2 = src[i + 2]; have = 3 }
|
|
let e0 = b0 >> 2
|
|
let e1 = ((b0 & 3) << 4) | (b1 >> 4)
|
|
let e2 = ((b1 & 15) << 2) | (b2 >> 6)
|
|
let e3 = b2 & 63
|
|
out = out + tab[e0..e0 + 1] + tab[e1..e1 + 1]
|
|
if have >= 2 { out = out + tab[e2..e2 + 1] } else { out = out + "=" }
|
|
if have >= 3 { out = out + tab[e3..e3 + 1] } else { out = out + "=" }
|
|
i = i + 3
|
|
}
|
|
return out
|
|
}
|