diff --git a/internal/cgen/base/token-public.h b/internal/cgen/base/token-public.h index c4d3b1d4..8dba5297 100644 --- a/internal/cgen/base/token-public.h +++ b/internal/cgen/base/token-public.h @@ -124,6 +124,8 @@ wuffs_base__make_token(uint64_t repr) { #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_STD 0x01000 #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_URL 0x02000 #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_4_DST_5_SRC_ASCII_85 0x04000 +#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_HEX 0x08000 +#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_STD 0x10000 // -------- diff --git a/internal/cgen/data/data.go b/internal/cgen/data/data.go index 11f8b9a2..79fab46b 100644 --- a/internal/cgen/data/data.go +++ b/internal/cgen/data/data.go @@ -565,7 +565,7 @@ const BaseTokenPublicH = "" + "" + "// --------\n\n// DEFINITELY_FOO means that the destination bytes (and also the source bytes,\n// for 1_DST_1_SRC_COPY) are in the FOO format. Definitely means that the lack\n// of the bit means \"maybe FOO\". It does not necessarily mean \"not FOO\".\n//\n// CHAIN_ETC means that decoding the entire token chain forms a UTF-8 or ASCII\n// string, not just this current token. CHAIN_ETC_UTF_8 therefore distinguishes\n// Unicode (UTF-8) strings from byte strings. MUST means that the the token\n// producer (e.g. parser) must verify this. SHOULD means that the token\n// consumer (e.g. renderer) should verify this.\n//\n// When a CHAIN_ETC_UTF_8 bit is set, the parser must ensure that non-ASCII\n// code points (with multi-byte UTF-8 encodings) do not straddle token\n// boundaries. Checking UTF-8 validity can inspect each token separately.\n//\n// The lack of any particular bit is conservative: it is valid for all-ASCII\n// strings, in a single- or multi-token chain, to have none of these bits set.\n#define WUFFS_BASE__TOKEN__VBD__STRING_" + "_DEFINITELY_UTF_8 0x00001\n#define WUFFS_BASE__TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 0x00002\n#define WUFFS_BASE__TOKEN__VBD__STRING__CHAIN_SHOULD_BE_UTF_8 0x00004\n#define WUFFS_BASE__TOKEN__VBD__STRING__DEFINITELY_ASCII 0x00010\n#define WUFFS_BASE__TOKEN__VBD__STRING__CHAIN_MUST_BE_ASCII 0x00020\n#define WUFFS_BASE__TOKEN__VBD__STRING__CHAIN_SHOULD_BE_ASCII 0x00040\n\n// CONVERT_D_DST_S_SRC means that multiples of S source bytes (possibly padded)\n// produces multiples of D destination bytes. For example,\n// CONVERT_1_DST_4_SRC_BACKSLASH_X means a source like \"\\\\x23\\\\x67\\\\xAB\", where\n// 12 src bytes encode 3 dst bytes.\n//\n// Post-processing may further transform those D destination bytes (e.g. treat\n// \"\\\\xFF\" as the Unicode code point U+00FF instead of the byte 0xFF), but that\n// is out of scope of this VBD's semantics.\n//\n// When src is the empty string, multiple conversion algorithms are applicable\n// (so these bits are not necessarily mutually exclusive), all producing the\n// same empty dst string.\n#define WU" + - "FFS_BASE__TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP 0x00100\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY 0x00200\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_2_SRC_HEXADECIMAL 0x00400\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_4_SRC_BACKSLASH_X 0x00800\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_STD 0x01000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_URL 0x02000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_4_DST_5_SRC_ASCII_85 0x04000\n\n" + + "FFS_BASE__TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP 0x00100\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY 0x00200\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_2_SRC_HEXADECIMAL 0x00400\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_1_DST_4_SRC_BACKSLASH_X 0x00800\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_STD 0x01000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_URL 0x02000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_4_DST_5_SRC_ASCII_85 0x04000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_HEX 0x08000\n#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_STD 0x10000\n\n" + "" + "// --------\n\n#define WUFFS_BASE__TOKEN__VBD__LITERAL__UNDEFINED 0x00001\n#define WUFFS_BASE__TOKEN__VBD__LITERAL__NULL 0x00002\n#define WUFFS_BASE__TOKEN__VBD__LITERAL__FALSE 0x00004\n#define WUFFS_BASE__TOKEN__VBD__LITERAL__TRUE 0x00008\n\n" + "" + diff --git a/lang/builtin/builtin.go b/lang/builtin/builtin.go index 44775f9c..764096a2 100644 --- a/lang/builtin/builtin.go +++ b/lang/builtin/builtin.go @@ -114,6 +114,8 @@ var Consts = [...]struct { {t.IDU32, "0x01000", "TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_STD"}, {t.IDU32, "0x02000", "TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_URL"}, {t.IDU32, "0x04000", "TOKEN__VBD__STRING__CONVERT_4_DST_5_SRC_ASCII_85"}, + {t.IDU32, "0x08000", "TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_HEX"}, + {t.IDU32, "0x10000", "TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_STD"}, // ---- diff --git a/release/c/wuffs-unsupported-snapshot.c b/release/c/wuffs-unsupported-snapshot.c index 52fc9df4..7f9259d9 100644 --- a/release/c/wuffs-unsupported-snapshot.c +++ b/release/c/wuffs-unsupported-snapshot.c @@ -2194,6 +2194,8 @@ wuffs_base__make_token(uint64_t repr) { #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_STD 0x01000 #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_3_DST_4_SRC_BASE_64_URL 0x02000 #define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_4_DST_5_SRC_ASCII_85 0x04000 +#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_HEX 0x08000 +#define WUFFS_BASE__TOKEN__VBD__STRING__CONVERT_5_DST_8_SRC_BASE_32_STD 0x10000 // --------