From b2912528bd3cbe1c40ec03eba18934b42b74ba8e Mon Sep 17 00:00:00 2001 From: anon Date: Sat, 14 Sep 2024 01:56:14 +0200 Subject: [PATCH] proper implementation in C --- Makefile | 27 +- library/kvec.h | 90 +++ library/sds.c | 1603 +++++++++++++++++++++++++++++++++++++++ library/sds.h | 155 ++++ library/sdsalloc.h | 47 ++ source/TBSP_strings.inc | 122 +++ source/tbc.c | 116 +++ source/tbc.cpp | 122 +-- source/tbsp.c | 112 +++ source/tbsp.l | 94 +++ source/tbsp.y | 126 +++ 11 files changed, 2550 insertions(+), 64 deletions(-) create mode 100644 library/kvec.h create mode 100644 library/sds.c create mode 100644 library/sds.h create mode 100644 library/sdsalloc.h create mode 100644 source/TBSP_strings.inc create mode 100644 source/tbc.c create mode 100644 source/tbsp.c create mode 100644 source/tbsp.l create mode 100644 source/tbsp.y diff --git a/Makefile b/Makefile index e455a77..746211e 100644 --- a/Makefile +++ b/Makefile @@ -1,9 +1,24 @@ .PHONY: main test -main: - g++ source/tbc.cpp $$(pkg-config --cflags --libs tree-sitter tree-sitter-c) -ggdb +CFLAGS := -std=c2x -Wall -Wpedantic -test: - python source/tbc.py test/convert.tbsp > object/kek.cpp - bake object/kek.cpp - ./object/a.out test/input.md +ifeq (${DEBUG}, 1) + LFLAGS += --debug --trace + YFLAGS += --debug + CFLAGS += -O0 -ggdb -fno-inline + CPPFLAGS += -DDEBUG +else + CFLAGS += -O3 -flto=auto -fno-stack-protector +endif + +OUT := tbsp + +main: + bison ${YFLAGS} --header=object/tbsp.tab.h -o object/tbsp.tab.c source/tbsp.y + flex ${LFLAGS} --header-file=object/tbsp.yy.h -o object/tbsp.yy.c source/tbsp.l + gcc ${CPPFLAGS} ${CFLAGS} -Iobject -Ilibrary object/tbsp.tab.c object/tbsp.yy.c source/tbsp.c library/sds.c -o ${OUT} + +run: + ./${OUT} test/convert.tbsp > object/test.cpp + bake object/test.cpp + ./object/test.out test/input.md diff --git a/library/kvec.h b/library/kvec.h new file mode 100644 index 0000000..676be8b --- /dev/null +++ b/library/kvec.h @@ -0,0 +1,90 @@ +/* The MIT License + + Copyright (c) 2008, by Attractive Chaos + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be + included in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. +*/ + +/* + An example: + +#include "kvec.h" +int main() { + kvec_t(int) array; + kv_init(array); + kv_push(int, array, 10); // append + kv_a(int, array, 20) = 5; // dynamic + kv_A(array, 20) = 4; // static + kv_destroy(array); + return 0; +} +*/ + +/* + 2008-09-22 (0.1.0): + + * The initial version. + +*/ + +#ifndef AC_KVEC_H +#define AC_KVEC_H + +#include + +#define kv_roundup32(x) (--(x), (x)|=(x)>>1, (x)|=(x)>>2, (x)|=(x)>>4, (x)|=(x)>>8, (x)|=(x)>>16, ++(x)) + +#define kvec_t(type) struct { size_t n, m; type *a; } +#define kv_init(v) ((v).n = (v).m = 0, (v).a = 0) +#define kv_destroy(v) free((v).a) +#define kv_A(v, i) ((v).a[(i)]) +#define kv_pop(v) ((v).a[--(v).n]) +#define kv_size(v) ((v).n) +#define kv_max(v) ((v).m) + +#define kv_resize(type, v, s) ((v).m = (s), (v).a = (type*)realloc((v).a, sizeof(type) * (v).m)) + +#define kv_copy(type, v1, v0) do { \ + if ((v1).m < (v0).n) kv_resize(type, v1, (v0).n); \ + (v1).n = (v0).n; \ + memcpy((v1).a, (v0).a, sizeof(type) * (v0).n); \ + } while (0) \ + +#define kv_push(type, v, x) do { \ + if ((v).n == (v).m) { \ + (v).m = (v).m? (v).m<<1 : 2; \ + (v).a = (type*)realloc((v).a, sizeof(type) * (v).m); \ + } \ + (v).a[(v).n++] = (x); \ + } while (0) + +#define kv_pushp(type, v) (((v).n == (v).m)? \ + ((v).m = ((v).m? (v).m<<1 : 2), \ + (v).a = (type*)realloc((v).a, sizeof(type) * (v).m), 0) \ + : 0), ((v).a + ((v).n++)) + +#define kv_a(type, v, i) (((v).m <= (size_t)(i)? \ + ((v).m = (v).n = (i) + 1, kv_roundup32((v).m), \ + (v).a = (type*)realloc((v).a, sizeof(type) * (v).m), 0) \ + : (v).n <= (size_t)(i)? (v).n = (i) + 1 \ + : 0), (v).a[(i)]) + +#endif diff --git a/library/sds.c b/library/sds.c new file mode 100644 index 0000000..349d27e --- /dev/null +++ b/library/sds.c @@ -0,0 +1,1603 @@ +/* SDSLib 2.2 -- A C dynamic strings library + * + * Copyright (c) 2006-2015, Salvatore Sanfilippo + * Copyright (c) 2015, Oran Agra + * Copyright (c) 2015, Redis Labs, Inc + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * * Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Redis nor the names of its contributors may be used + * to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "sds.h" +#include "sdsalloc.h" + +#undef NDEBUG +#include + +#include +#include +#include +#include +#include + +const char *SDS_NOINIT = "SDS_NOINIT"; + +inline size_t sdslen(const sds s) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: + return SDS_TYPE_5_LEN(flags); + case SDS_TYPE_8: + return SDS_HDR(8,s)->len; + case SDS_TYPE_16: + return SDS_HDR(16,s)->len; + case SDS_TYPE_32: + return SDS_HDR(32,s)->len; + case SDS_TYPE_64: + return SDS_HDR(64,s)->len; + } + return 0; +} + +inline size_t sdsavail(const sds s) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: { + return 0; + } + case SDS_TYPE_8: { + SDS_HDR_VAR(8,s); + return sh->alloc - sh->len; + } + case SDS_TYPE_16: { + SDS_HDR_VAR(16,s); + return sh->alloc - sh->len; + } + case SDS_TYPE_32: { + SDS_HDR_VAR(32,s); + return sh->alloc - sh->len; + } + case SDS_TYPE_64: { + SDS_HDR_VAR(64,s); + return sh->alloc - sh->len; + } + } + return 0; +} + +inline void sdssetlen(sds s, size_t newlen) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: + { + unsigned char *fp = ((unsigned char*)s)-1; + *fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS); + } + break; + case SDS_TYPE_8: + SDS_HDR(8,s)->len = newlen; + break; + case SDS_TYPE_16: + SDS_HDR(16,s)->len = newlen; + break; + case SDS_TYPE_32: + SDS_HDR(32,s)->len = newlen; + break; + case SDS_TYPE_64: + SDS_HDR(64,s)->len = newlen; + break; + } +} + +inline void sdsinclen(sds s, size_t inc) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: + { + unsigned char *fp = ((unsigned char*)s)-1; + unsigned char newlen = SDS_TYPE_5_LEN(flags)+inc; + *fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS); + } + break; + case SDS_TYPE_8: + SDS_HDR(8,s)->len += inc; + break; + case SDS_TYPE_16: + SDS_HDR(16,s)->len += inc; + break; + case SDS_TYPE_32: + SDS_HDR(32,s)->len += inc; + break; + case SDS_TYPE_64: + SDS_HDR(64,s)->len += inc; + break; + } +} + +/* sdsalloc() = sdsavail() + sdslen() */ +inline size_t sdsalloc(const sds s) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: + return SDS_TYPE_5_LEN(flags); + case SDS_TYPE_8: + return SDS_HDR(8,s)->alloc; + case SDS_TYPE_16: + return SDS_HDR(16,s)->alloc; + case SDS_TYPE_32: + return SDS_HDR(32,s)->alloc; + case SDS_TYPE_64: + return SDS_HDR(64,s)->alloc; + } + return 0; +} + +inline void sdssetalloc(sds s, size_t newlen) { + unsigned char flags = s[-1]; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: + /* Nothing to do, this type has no total allocation info. */ + break; + case SDS_TYPE_8: + SDS_HDR(8,s)->alloc = newlen; + break; + case SDS_TYPE_16: + SDS_HDR(16,s)->alloc = newlen; + break; + case SDS_TYPE_32: + SDS_HDR(32,s)->alloc = newlen; + break; + case SDS_TYPE_64: + SDS_HDR(64,s)->alloc = newlen; + break; + } +} + +static inline int sdsHdrSize(char type) { + switch(type&SDS_TYPE_MASK) { + case SDS_TYPE_5: + return sizeof(struct sdshdr5); + case SDS_TYPE_8: + return sizeof(struct sdshdr8); + case SDS_TYPE_16: + return sizeof(struct sdshdr16); + case SDS_TYPE_32: + return sizeof(struct sdshdr32); + case SDS_TYPE_64: + return sizeof(struct sdshdr64); + } + return 0; +} + +static inline char sdsReqType(size_t string_size) { + if (string_size < 1<<5) + return SDS_TYPE_5; + if (string_size < 1<<8) + return SDS_TYPE_8; + if (string_size < 1<<16) + return SDS_TYPE_16; +#if (LONG_MAX == LLONG_MAX) + if (string_size < 1ll<<32) + return SDS_TYPE_32; + return SDS_TYPE_64; +#else + return SDS_TYPE_32; +#endif +} + +/* Create a new sds string with the content specified by the 'init' pointer + * and 'initlen'. + * If NULL is used for 'init' the string is initialized with zero bytes. + * If SDS_NOINIT is used, the buffer is left uninitialized; + * + * The string is always null-terminated (all the sds strings are, always) so + * even if you create an sds string with: + * + * mystring = sdsnewlen("abc",3); + * + * You can print the string with printf() as there is an implicit \0 at the + * end of the string. However the string is binary safe and can contain + * \0 characters in the middle, as the length is stored in the sds header. */ +sds sdsnewlen(const void *init, size_t initlen) { + void *newsh; + sds s; + char type = sdsReqType(initlen); + /* Empty strings are usually created in order to append. Use type 8 + * since type 5 is not good at this. */ + if (type == SDS_TYPE_5 && initlen == 0) type = SDS_TYPE_8; + int hdrlen = sdsHdrSize(type); + unsigned char *fp; /* flags pointer. */ + + assert(initlen + hdrlen + 1 > initlen); /* Catch size_t overflow */ + newsh = s_malloc(hdrlen+initlen+1); + if (newsh == NULL) return NULL; + if (init==SDS_NOINIT) + init = NULL; + else if (!init) + memset(newsh, 0, hdrlen+initlen+1); + s = (char*)newsh+hdrlen; + fp = ((unsigned char*)s)-1; + switch(type) { + case SDS_TYPE_5: { + *fp = type | (initlen << SDS_TYPE_BITS); + break; + } + case SDS_TYPE_8: { + SDS_HDR_VAR(8,s); + sh->len = initlen; + sh->alloc = initlen; + *fp = type; + break; + } + case SDS_TYPE_16: { + SDS_HDR_VAR(16,s); + sh->len = initlen; + sh->alloc = initlen; + *fp = type; + break; + } + case SDS_TYPE_32: { + SDS_HDR_VAR(32,s); + sh->len = initlen; + sh->alloc = initlen; + *fp = type; + break; + } + case SDS_TYPE_64: { + SDS_HDR_VAR(64,s); + sh->len = initlen; + sh->alloc = initlen; + *fp = type; + break; + } + } + if (initlen && init) + memcpy(s, init, initlen); + s[initlen] = '\0'; + return s; +} + +/* Create an empty (zero length) sds string. Even in this case the string + * always has an implicit null term. */ +sds sdsempty(void) { + return sdsnewlen("",0); +} + +/* Create a new sds string starting from a null terminated C string. */ +sds sdsnew(const char *init) { + size_t initlen = (init == NULL) ? 0 : strlen(init); + return sdsnewlen(init, initlen); +} + +/* Duplicate an sds string. */ +sds sdsdup(const sds s) { + return sdsnewlen(s, sdslen(s)); +} + +/* Free an sds string. No operation is performed if 's' is NULL. */ +void sdsfree(sds s) { + if (s == NULL) return; + s_free((char*)s-sdsHdrSize(s[-1])); +} + +/* Set the sds string length to the length as obtained with strlen(), so + * considering as content only up to the first null term character. + * + * This function is useful when the sds string is hacked manually in some + * way, like in the following example: + * + * s = sdsnew("foobar"); + * s[2] = '\0'; + * sdsupdatelen(s); + * printf("%d\n", sdslen(s)); + * + * The output will be "2", but if we comment out the call to sdsupdatelen() + * the output will be "6" as the string was modified but the logical length + * remains 6 bytes. */ +void sdsupdatelen(sds s) { + size_t reallen = strlen(s); + sdssetlen(s, reallen); +} + +/* Modify an sds string in-place to make it empty (zero length). + * However all the existing buffer is not discarded but set as free space + * so that next append operations will not require allocations up to the + * number of bytes previously available. */ +void sdsclear(sds s) { + sdssetlen(s, 0); + s[0] = '\0'; +} + +/* Enlarge the free space at the end of the sds string so that the caller + * is sure that after calling this function can overwrite up to addlen + * bytes after the end of the string, plus one more byte for nul term. + * + * Note: this does not change the *length* of the sds string as returned + * by sdslen(), but only the free buffer space we have. */ +sds sdsMakeRoomFor(sds s, size_t addlen) { + void *sh, *newsh; + size_t avail = sdsavail(s); + size_t len, newlen, reqlen; + char type, oldtype = s[-1] & SDS_TYPE_MASK; + int hdrlen; + + /* Return ASAP if there is enough space left. */ + if (avail >= addlen) return s; + + len = sdslen(s); + sh = (char*)s-sdsHdrSize(oldtype); + reqlen = newlen = (len+addlen); + if (newlen < SDS_MAX_PREALLOC) + newlen *= 2; + else + newlen += SDS_MAX_PREALLOC; + + type = sdsReqType(newlen); + + /* Don't use type 5: the user is appending to the string and type 5 is + * not able to remember empty space, so sdsMakeRoomFor() must be called + * at every appending operation. */ + if (type == SDS_TYPE_5) type = SDS_TYPE_8; + + hdrlen = sdsHdrSize(type); + assert(hdrlen + newlen + 1 > reqlen); /* Catch size_t overflow */ + if (oldtype==type) { + newsh = s_realloc(sh, hdrlen+newlen+1); + if (newsh == NULL) return NULL; + s = (char*)newsh+hdrlen; + } else { + /* Since the header size changes, need to move the string forward, + * and can't use realloc */ + newsh = s_malloc(hdrlen+newlen+1); + if (newsh == NULL) return NULL; + memcpy((char*)newsh+hdrlen, s, len+1); + s_free(sh); + s = (char*)newsh+hdrlen; + s[-1] = type; + sdssetlen(s, len); + } + sdssetalloc(s, newlen); + return s; +} + +/* Reallocate the sds string so that it has no free space at the end. The + * contained string remains not altered, but next concatenation operations + * will require a reallocation. + * + * After the call, the passed sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. */ +sds sdsRemoveFreeSpace(sds s) { + void *sh, *newsh; + char type, oldtype = s[-1] & SDS_TYPE_MASK; + int hdrlen, oldhdrlen = sdsHdrSize(oldtype); + size_t len = sdslen(s); + size_t avail = sdsavail(s); + sh = (char*)s-oldhdrlen; + + /* Return ASAP if there is no space left. */ + if (avail == 0) return s; + + /* Check what would be the minimum SDS header that is just good enough to + * fit this string. */ + type = sdsReqType(len); + hdrlen = sdsHdrSize(type); + + /* If the type is the same, or at least a large enough type is still + * required, we just realloc(), letting the allocator to do the copy + * only if really needed. Otherwise if the change is huge, we manually + * reallocate the string to use the different header type. */ + if (oldtype==type || type > SDS_TYPE_8) { + newsh = s_realloc(sh, oldhdrlen+len+1); + if (newsh == NULL) return NULL; + s = (char*)newsh+oldhdrlen; + } else { + newsh = s_malloc(hdrlen+len+1); + if (newsh == NULL) return NULL; + memcpy((char*)newsh+hdrlen, s, len+1); + s_free(sh); + s = (char*)newsh+hdrlen; + s[-1] = type; + sdssetlen(s, len); + } + sdssetalloc(s, len); + return s; +} + +/* Resize the allocation, this can make the allocation bigger or smaller, + * if the size is smaller than currently used len, the data will be truncated */ +sds sdsResize(sds s, size_t size) { + void *sh, *newsh; + char type, oldtype = s[-1] & SDS_TYPE_MASK; + int hdrlen, oldhdrlen = sdsHdrSize(oldtype); + size_t len = sdslen(s); + sh = (char*)s-oldhdrlen; + + /* Return ASAP if the size is already good. */ + if (sdsalloc(s) == size) return s; + + /* Truncate len if needed. */ + if (size < len) len = size; + + /* Check what would be the minimum SDS header that is just good enough to + * fit this string. */ + type = sdsReqType(size); + /* Don't use type 5, it is not good for strings that are resized. */ + if (type == SDS_TYPE_5) type = SDS_TYPE_8; + hdrlen = sdsHdrSize(type); + + /* If the type is the same, or can hold the size in it with low overhead + * (larger than SDS_TYPE_8), we just realloc(), letting the allocator + * to do the copy only if really needed. Otherwise if the change is + * huge, we manually reallocate the string to use the different header + * type. */ + if (oldtype==type || (type < oldtype && type > SDS_TYPE_8)) { + newsh = s_realloc(sh, oldhdrlen+size+1); + if (newsh == NULL) return NULL; + s = (char*)newsh+oldhdrlen; + } else { + newsh = s_malloc(hdrlen+size+1); + if (newsh == NULL) return NULL; + memcpy((char*)newsh+hdrlen, s, len); + s_free(sh); + s = (char*)newsh+hdrlen; + s[-1] = type; + } + s[len] = 0; + sdssetlen(s, len); + sdssetalloc(s, size); + return s; +} + +/* Return the total size of the allocation of the specified sds string, + * including: + * 1) The sds header before the pointer. + * 2) The string. + * 3) The free buffer at the end if any. + * 4) The implicit null term. + */ +size_t sdsAllocSize(sds s) { + size_t alloc = sdsalloc(s); + return sdsHdrSize(s[-1])+alloc+1; +} + +/* Return the pointer of the actual SDS allocation (normally SDS strings + * are referenced by the start of the string buffer). */ +void *sdsAllocPtr(sds s) { + return (void*) (s-sdsHdrSize(s[-1])); +} + +/* Increment the sds length and decrements the left free space at the + * end of the string according to 'incr'. Also set the null term + * in the new end of the string. + * + * This function is used in order to fix the string length after the + * user calls sdsMakeRoomFor(), writes something after the end of + * the current string, and finally needs to set the new length. + * + * Note: it is possible to use a negative increment in order to + * right-trim the string. + * + * Usage example: + * + * Using sdsIncrLen() and sdsMakeRoomFor() it is possible to mount the + * following schema, to cat bytes coming from the kernel to the end of an + * sds string without copying into an intermediate buffer: + * + * oldlen = sdslen(s); + * s = sdsMakeRoomFor(s, BUFFER_SIZE); + * nread = read(fd, s+oldlen, BUFFER_SIZE); + * ... check for nread <= 0 and handle it ... + * sdsIncrLen(s, nread); + */ +void sdsIncrLen(sds s, ssize_t incr) { + unsigned char flags = s[-1]; + size_t len; + switch(flags&SDS_TYPE_MASK) { + case SDS_TYPE_5: { + unsigned char *fp = ((unsigned char*)s)-1; + unsigned char oldlen = SDS_TYPE_5_LEN(flags); + assert((incr > 0 && oldlen+incr < 32) || (incr < 0 && oldlen >= (unsigned int)(-incr))); + *fp = SDS_TYPE_5 | ((oldlen+incr) << SDS_TYPE_BITS); + len = oldlen+incr; + break; + } + case SDS_TYPE_8: { + SDS_HDR_VAR(8,s); + assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr))); + len = (sh->len += incr); + break; + } + case SDS_TYPE_16: { + SDS_HDR_VAR(16,s); + assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr))); + len = (sh->len += incr); + break; + } + case SDS_TYPE_32: { + SDS_HDR_VAR(32,s); + assert((incr >= 0 && sh->alloc-sh->len >= (unsigned int)incr) || (incr < 0 && sh->len >= (unsigned int)(-incr))); + len = (sh->len += incr); + break; + } + case SDS_TYPE_64: { + SDS_HDR_VAR(64,s); + assert((incr >= 0 && sh->alloc-sh->len >= (uint64_t)incr) || (incr < 0 && sh->len >= (uint64_t)(-incr))); + len = (sh->len += incr); + break; + } + default: len = 0; /* Just to avoid compilation warnings. */ + } + s[len] = '\0'; +} + +/* Grow the sds to have the specified length. Bytes that were not part of + * the original length of the sds will be set to zero. + * + * if the specified length is smaller than the current length, no operation + * is performed. */ +sds sdsgrowzero(sds s, size_t len) { + size_t curlen = sdslen(s); + + if (len <= curlen) return s; + s = sdsMakeRoomFor(s,len-curlen); + if (s == NULL) return NULL; + + /* Make sure added region doesn't contain garbage */ + memset(s+curlen,0,(len-curlen+1)); /* also set trailing \0 byte */ + sdssetlen(s, len); + return s; +} + +/* Append the specified binary-safe string pointed by 't' of 'len' bytes to the + * end of the specified sds string 's'. + * + * After the call, the passed sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. */ +sds sdscatlen(sds s, const void *t, size_t len) { + size_t curlen = sdslen(s); + + s = sdsMakeRoomFor(s,len); + if (s == NULL) return NULL; + memcpy(s+curlen, t, len); + sdssetlen(s, curlen+len); + s[curlen+len] = '\0'; + return s; +} + +/* Append the specified null terminated C string to the sds string 's'. + * + * After the call, the passed sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. */ +sds sdscat(sds s, const char *t) { + return sdscatlen(s, t, strlen(t)); +} + +/* Append the specified sds 't' to the existing sds 's'. + * + * After the call, the modified sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. */ +sds sdscatsds(sds s, const sds t) { + return sdscatlen(s, t, sdslen(t)); +} + +/* Destructively modify the sds string 's' to hold the specified binary + * safe string pointed by 't' of length 'len' bytes. */ +sds sdscpylen(sds s, const char *t, size_t len) { + if (sdsalloc(s) < len) { + s = sdsMakeRoomFor(s,len-sdslen(s)); + if (s == NULL) return NULL; + } + memcpy(s, t, len); + s[len] = '\0'; + sdssetlen(s, len); + return s; +} + +/* Like sdscpylen() but 't' must be a null-terminated string so that the length + * of the string is obtained with strlen(). */ +sds sdscpy(sds s, const char *t) { + return sdscpylen(s, t, strlen(t)); +} + +/* Helper for sdscatlonglong() doing the actual number -> string + * conversion. 's' must point to a string with room for at least + * SDS_LLSTR_SIZE bytes. + * + * The function returns the length of the null-terminated string + * representation stored at 's'. */ +#define SDS_LLSTR_SIZE 21 +int sdsll2str(char *s, long long value) { + char *p, aux; + unsigned long long v; + size_t l; + + /* Generate the string representation, this method produces + * a reversed string. */ + if (value < 0) { + /* Since v is unsigned, if value==LLONG_MIN then + * -LLONG_MIN will overflow. */ + if (value != LLONG_MIN) { + v = -value; + } else { + v = ((unsigned long long)LLONG_MAX) + 1; + } + } else { + v = value; + } + + p = s; + do { + *p++ = '0'+(v%10); + v /= 10; + } while(v); + if (value < 0) *p++ = '-'; + + /* Compute length and add null term. */ + l = p-s; + *p = '\0'; + + /* Reverse the string. */ + p--; + while(s < p) { + aux = *s; + *s = *p; + *p = aux; + s++; + p--; + } + return l; +} + +/* Identical sdsll2str(), but for unsigned long long type. */ +int sdsull2str(char *s, unsigned long long v) { + char *p, aux; + size_t l; + + /* Generate the string representation, this method produces + * a reversed string. */ + p = s; + do { + *p++ = '0'+(v%10); + v /= 10; + } while(v); + + /* Compute length and add null term. */ + l = p-s; + *p = '\0'; + + /* Reverse the string. */ + p--; + while(s < p) { + aux = *s; + *s = *p; + *p = aux; + s++; + p--; + } + return l; +} + +/* Create an sds string from a long long value. It is much faster than: + * + * sdscatprintf(sdsempty(),"%lld\n", value); + */ +sds sdsfromlonglong(long long value) { + char buf[SDS_LLSTR_SIZE]; + int len = sdsll2str(buf,value); + + return sdsnewlen(buf,len); +} + +/* Like sdscatprintf() but gets va_list instead of being variadic. */ +sds sdscatvprintf(sds s, const char *fmt, va_list ap) { + va_list cpy; + char staticbuf[1024], *buf = staticbuf, *t; + size_t buflen = strlen(fmt)*2; + int bufstrlen; + + /* We try to start using a static buffer for speed. + * If not possible we revert to heap allocation. */ + if (buflen > sizeof(staticbuf)) { + buf = s_malloc(buflen); + if (buf == NULL) return NULL; + } else { + buflen = sizeof(staticbuf); + } + + /* Alloc enough space for buffer and \0 after failing to + * fit the string in the current buffer size. */ + while(1) { + va_copy(cpy,ap); + bufstrlen = vsnprintf(buf, buflen, fmt, cpy); + va_end(cpy); + if (bufstrlen < 0) { + if (buf != staticbuf) s_free(buf); + return NULL; + } + if (((size_t)bufstrlen) >= buflen) { + if (buf != staticbuf) s_free(buf); + buflen = ((size_t)bufstrlen) + 1; + buf = s_malloc(buflen); + if (buf == NULL) return NULL; + continue; + } + break; + } + + /* Finally concat the obtained string to the SDS string and return it. */ + t = sdscatlen(s, buf, bufstrlen); + if (buf != staticbuf) s_free(buf); + return t; +} + +/* Append to the sds string 's' a string obtained using printf-alike format + * specifier. + * + * After the call, the modified sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. + * + * Example: + * + * s = sdsnew("Sum is: "); + * s = sdscatprintf(s,"%d+%d = %d",a,b,a+b). + * + * Often you need to create a string from scratch with the printf-alike + * format. When this is the need, just use sdsempty() as the target string: + * + * s = sdscatprintf(sdsempty(), "... your format ...", args); + */ +sds sdscatprintf(sds s, const char *fmt, ...) { + va_list ap; + char *t; + va_start(ap, fmt); + t = sdscatvprintf(s,fmt,ap); + va_end(ap); + return t; +} + +/* This function is similar to sdscatprintf, but much faster as it does + * not rely on sprintf() family functions implemented by the libc that + * are often very slow. Moreover directly handling the sds string as + * new data is concatenated provides a performance improvement. + * + * However this function only handles an incompatible subset of printf-alike + * format specifiers: + * + * %c - char + * %s - C String + * %S - SDS string + * %i - signed int + * %l - signed long + * %I - 64 bit signed integer (long long, int64_t) + * %u - unsigned int + * %L - unsigned long + * %U - 64 bit unsigned integer (unsigned long long, uint64_t) + * %% - Verbatim "%" character. + */ +sds sdscatfmt(sds s, char const *fmt, ...) { + size_t initlen = sdslen(s); + const char *f = fmt; + long i; + va_list ap; + + /* To avoid continuous reallocations, let's start with a buffer that + * can hold at least two times the format string itself. It's not the + * best heuristic but seems to work in practice. */ + s = sdsMakeRoomFor(s, strlen(fmt)*2); + va_start(ap,fmt); + f = fmt; /* Next format specifier byte to process. */ + i = initlen; /* Position of the next byte to write to dest str. */ + while(*f) { + char next, *str; + size_t l; + long long num; + unsigned long long unum; + + /* Make sure there is always space for at least 1 char. */ + if (sdsavail(s)==0) { + s = sdsMakeRoomFor(s,1); + } + + switch(*f) { + case '%': + next = *(f+1); + if (next == '\0') break; + f++; + switch(next) { + case 'c': + num = va_arg(ap,int); + s[i++] = num; + sdsinclen(s,1); + break; + case 's': + case 'S': + str = va_arg(ap,char*); + l = (next == 's') ? strlen(str) : sdslen(str); + if (sdsavail(s) < l) { + s = sdsMakeRoomFor(s,l); + } + memcpy(s+i,str,l); + sdsinclen(s,l); + i += l; + break; + case 'i': + case 'I': + case 'l': + if (next == 'i') + num = va_arg(ap,int); + else if (next == 'l') + num = va_arg(ap,long); + else + num = va_arg(ap,long long); + { + char buf[SDS_LLSTR_SIZE]; + l = sdsll2str(buf,num); + if (sdsavail(s) < l) { + s = sdsMakeRoomFor(s,l); + } + memcpy(s+i,buf,l); + sdsinclen(s,l); + i += l; + } + break; + case 'u': + case 'U': + case 'L': + if (next == 'u') + unum = va_arg(ap,unsigned int); + else if (next == 'L') + unum = va_arg(ap,unsigned long); + else + unum = va_arg(ap,unsigned long long); + { + char buf[SDS_LLSTR_SIZE]; + l = sdsull2str(buf,unum); + if (sdsavail(s) < l) { + s = sdsMakeRoomFor(s,l); + } + memcpy(s+i,buf,l); + sdsinclen(s,l); + i += l; + } + break; + default: /* Handle %% and generally %. */ + s[i++] = next; + sdsinclen(s,1); + break; + } + break; + default: + s[i++] = *f; + sdsinclen(s,1); + break; + } + f++; + } + va_end(ap); + + /* Add null-term */ + s[i] = '\0'; + return s; +} + +/* Remove the part of the string from left and from right composed just of + * contiguous characters found in 'cset', that is a null terminated C string. + * + * Example: + * + * s = sdsnew("AA...AA.a.aa.aHelloWorld :::"); + * sdstrim(s,"Aa. :"); + * printf("%s\n", s); + * + * Output will be just "HelloWorld". + */ +void sdstrim(sds s, const char *cset) { + char *end, *sp, *ep; + size_t len; + + sp = s; + ep = end = s+sdslen(s)-1; + while(sp <= end && strchr(cset, *sp)) sp++; + while(ep > sp && strchr(cset, *ep)) ep--; + len = (ep-sp)+1; + if (s != sp) memmove(s, sp, len); + s[len] = '\0'; + sdssetlen(s,len); +} + +/* Changes the input string to be a subset of the original. + * It does not release the free space in the string, so a call to + * sdsRemoveFreeSpace may be wise after. + */ +void sdssubstr(sds s, size_t start, size_t len) { + /* Clamp out of range input */ + size_t oldlen = sdslen(s); + if (start >= oldlen) start = len = 0; + if (len > oldlen-start) len = oldlen-start; + + /* Move the data */ + if (len) memmove(s, s+start, len); + s[len] = 0; + sdssetlen(s,len); +} + +/* Turn the string into a smaller (or equal) string containing only the + * substring specified by the 'start' and 'end' indexes. + * + * start and end can be negative, where -1 means the last character of the + * string, -2 the penultimate character, and so forth. + * + * The interval is inclusive, so the start and end characters will be part + * of the resulting string. + * + * The string is modified in-place. + * + * NOTE: this function can be misleading and can have unexpected behaviour, + * specifically when you want the length of the new string to be 0. + * Having start==end will result in a string with one character. + * please consider using sdssubstr instead. + * + * Example: + * + * s = sdsnew("Hello World"); + * sdsrange(s,1,-1); => "ello World" + */ +void sdsrange(sds s, ssize_t start, ssize_t end) { + size_t newlen, len = sdslen(s); + + if (len == 0) return; + if (start < 0) + start = len + start; + if (end < 0) + end = len + end; + newlen = (start > end) ? 0 : (end-start)+1; + sdssubstr(s, start, newlen); +} + +/* Apply tolower() to every character of the sds string 's'. */ +void sdstolower(sds s) { + size_t len = sdslen(s), j; + + for (j = 0; j < len; j++) s[j] = tolower(s[j]); +} + +/* Apply toupper() to every character of the sds string 's'. */ +void sdstoupper(sds s) { + size_t len = sdslen(s), j; + + for (j = 0; j < len; j++) s[j] = toupper(s[j]); +} + +/* Compare two sds strings s1 and s2 with memcmp(). + * + * Return value: + * + * positive if s1 > s2. + * negative if s1 < s2. + * 0 if s1 and s2 are exactly the same binary string. + * + * If two strings share exactly the same prefix, but one of the two has + * additional characters, the longer string is considered to be greater than + * the smaller one. */ +int sdscmp(const sds s1, const sds s2) { + size_t l1, l2, minlen; + int cmp; + + l1 = sdslen(s1); + l2 = sdslen(s2); + minlen = (l1 < l2) ? l1 : l2; + cmp = memcmp(s1,s2,minlen); + if (cmp == 0) return l1>l2? 1: (l1". + * + * After the call, the modified sds string is no longer valid and all the + * references must be substituted with the new pointer returned by the call. */ +sds sdscatrepr(sds s, const char *p, size_t len) { + s = sdscatlen(s,"\"",1); + while(len--) { + switch(*p) { + case '\\': + case '"': + s = sdscatfmt(s,"\\%c",*p); + break; + case '\n': s = sdscatlen(s,"\\n",2); break; + case '\r': s = sdscatlen(s,"\\r",2); break; + case '\t': s = sdscatlen(s,"\\t",2); break; + case '\a': s = sdscatlen(s,"\\a",2); break; + case '\b': s = sdscatlen(s,"\\b",2); break; + default: + if (isprint((int) (*p))) + s = sdscatfmt(s,"%c",*p); + else + s = sdscatprintf(s,"\\x%02x",(unsigned char)*p); + break; + } + p++; + } + return sdscatlen(s,"\"",1); +} + +/* Returns one if the string contains characters to be escaped + * by sdscatrepr(), zero otherwise. + * + * Typically, this should be used to help protect aggregated strings in a way + * that is compatible with sdssplitargs(). For this reason, also spaces will be + * treated as needing an escape. + */ +int sdsneedsrepr(const sds s) { + size_t len = sdslen(s); + const char *p = s; + + while (len--) { + if (*p == '\\' || *p == '"' || *p == '\n' || *p == '\r' || + *p == '\t' || *p == '\a' || *p == '\b' || !isprint((int) (*p)) || isspace((int) (*p))) return 1; + p++; + } + + return 0; +} + +/* Helper function for sdssplitargs() that returns non zero if 'c' + * is a valid hex digit. */ +static int is_hex_digit(char c) { + return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || + (c >= 'A' && c <= 'F'); +} + +/* Helper function for sdssplitargs() that converts a hex digit into an + * integer from 0 to 15 */ +static int hex_digit_to_int(char c) { + switch(c) { + case '0': return 0; + case '1': return 1; + case '2': return 2; + case '3': return 3; + case '4': return 4; + case '5': return 5; + case '6': return 6; + case '7': return 7; + case '8': return 8; + case '9': return 9; + case 'a': case 'A': return 10; + case 'b': case 'B': return 11; + case 'c': case 'C': return 12; + case 'd': case 'D': return 13; + case 'e': case 'E': return 14; + case 'f': case 'F': return 15; + default: return 0; + } +} + +/* Split a line into arguments, where every argument can be in the + * following programming-language REPL-alike form: + * + * foo bar "newline are supported\n" and "\xff\x00otherstuff" + * + * The number of arguments is stored into *argc, and an array + * of sds is returned. + * + * The caller should free the resulting array of sds strings with + * sdsfreesplitres(). + * + * Note that sdscatrepr() is able to convert back a string into + * a quoted string in the same format sdssplitargs() is able to parse. + * + * The function returns the allocated tokens on success, even when the + * input string is empty, or NULL if the input contains unbalanced + * quotes or closed quotes followed by non space characters + * as in: "foo"bar or "foo' + */ +sds *sdssplitargs(const char *line, int *argc) { + const char *p = line; + char *current = NULL; + char **vector = NULL; + + *argc = 0; + while(1) { + /* skip blanks */ + while(*p && isspace((int) (*p))) p++; + if (*p) { + /* get a token */ + int inq=0; /* set to 1 if we are in "quotes" */ + int insq=0; /* set to 1 if we are in 'single quotes' */ + int done=0; + + if (current == NULL) current = sdsempty(); + while(!done) { + if (inq) { + if (*p == '\\' && *(p+1) == 'x' && + is_hex_digit(*(p+2)) && + is_hex_digit(*(p+3))) + { + unsigned char byte; + + byte = (hex_digit_to_int(*(p+2))*16)+ + hex_digit_to_int(*(p+3)); + current = sdscatlen(current,(char*)&byte,1); + p += 3; + } else if (*p == '\\' && *(p+1)) { + char c; + + p++; + switch(*p) { + case 'n': c = '\n'; break; + case 'r': c = '\r'; break; + case 't': c = '\t'; break; + case 'b': c = '\b'; break; + case 'a': c = '\a'; break; + default: c = *p; break; + } + current = sdscatlen(current,&c,1); + } else if (*p == '"') { + /* closing quote must be followed by a space or + * nothing at all. */ + if (*(p+1) && !isspace((int) (*(p+1)))) goto err; + done=1; + } else if (!*p) { + /* unterminated quotes */ + goto err; + } else { + current = sdscatlen(current,p,1); + } + } else if (insq) { + if (*p == '\\' && *(p+1) == '\'') { + p++; + current = sdscatlen(current,"'",1); + } else if (*p == '\'') { + /* closing quote must be followed by a space or + * nothing at all. */ + if (*(p+1) && !isspace((int) (*(p+1)))) goto err; + done=1; + } else if (!*p) { + /* unterminated quotes */ + goto err; + } else { + current = sdscatlen(current,p,1); + } + } else { + switch(*p) { + case ' ': + case '\n': + case '\r': + case '\t': + case '\0': + done=1; + break; + case '"': + inq=1; + break; + case '\'': + insq=1; + break; + default: + current = sdscatlen(current,p,1); + break; + } + } + if (*p) p++; + } + /* add the token to the vector */ + vector = s_realloc(vector,((*argc)+1)*sizeof(char*)); + if (vector == NULL) goto err; + vector[*argc] = current; + (*argc)++; + current = NULL; + } else { + /* Even on empty input string return something not NULL. */ + if (vector == NULL) vector = s_malloc(sizeof(void*)); + return vector; + } + } + +err: + while((*argc)--) + sdsfree(vector[*argc]); + s_free(vector); + if (current) sdsfree(current); + *argc = 0; + return NULL; +} + +/* Modify the string substituting all the occurrences of the set of + * characters specified in the 'from' string to the corresponding character + * in the 'to' array. + * + * For instance: sdsmapchars(mystring, "ho", "01", 2) + * will have the effect of turning the string "hello" into "0ell1". + * + * The function returns the sds string pointer, that is always the same + * as the input pointer since no resize is needed. */ +sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen) { + size_t j, i, l = sdslen(s); + + for (j = 0; j < l; j++) { + for (i = 0; i < setlen; i++) { + if (s[j] == from[i]) { + s[j] = to[i]; + break; + } + } + } + return s; +} + +/* Join an array of C strings using the specified separator (also a C string). + * Returns the result as an sds string. */ +sds sdsjoin(char **argv, int argc, char *sep) { + sds join = sdsempty(); + int j; + + for (j = 0; j < argc; j++) { + join = sdscat(join, argv[j]); + if (j != argc-1) join = sdscat(join,sep); + } + return join; +} + +/* Like sdsjoin, but joins an array of SDS strings. */ +sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen) { + sds join = sdsempty(); + int j; + + for (j = 0; j < argc; j++) { + join = sdscatsds(join, argv[j]); + if (j != argc-1) join = sdscatlen(join,sep,seplen); + } + return join; +} + +/* Wrappers to the allocators used by SDS. Note that SDS will actually + * just use the macros defined into sdsalloc.h in order to avoid to pay + * the overhead of function calls. Here we define these wrappers only for + * the programs SDS is linked to, if they want to touch the SDS internals + * even if they use a different allocator. */ +void *sds_malloc(size_t size) { return s_malloc(size); } +void *sds_realloc(void *ptr, size_t size) { return s_realloc(ptr,size); } +void sds_free(void *ptr) { s_free(ptr); } + +#if defined(SDS_TEST_MAIN) +#include +#include "testhelp.h" +#include "limits.h" + +#define UNUSED(x) (void)(x) +int sdsTest(void) { + { + sds x = sdsnew("foo"), y; + + test_cond("Create a string and obtain the length", + sdslen(x) == 3 && memcmp(x,"foo\0",4) == 0); + + sdsfree(x); + x = sdsnewlen("foo",2); + test_cond("Create a string with specified length", + sdslen(x) == 2 && memcmp(x,"fo\0",3) == 0); + + x = sdscat(x,"bar"); + test_cond("Strings concatenation", + sdslen(x) == 5 && memcmp(x,"fobar\0",6) == 0); + + x = sdscpy(x,"a"); + test_cond("sdscpy() against an originally longer string", + sdslen(x) == 1 && memcmp(x,"a\0",2) == 0); + + x = sdscpy(x,"xyzxxxxxxxxxxyyyyyyyyyykkkkkkkkkk"); + test_cond("sdscpy() against an originally shorter string", + sdslen(x) == 33 && + memcmp(x,"xyzxxxxxxxxxxyyyyyyyyyykkkkkkkkkk\0",33) == 0); + + sdsfree(x); + x = sdscatprintf(sdsempty(),"%d",123); + test_cond("sdscatprintf() seems working in the base case", + sdslen(x) == 3 && memcmp(x,"123\0",4) == 0); + + sdsfree(x); + x = sdscatprintf(sdsempty(),"a%cb",0); + test_cond("sdscatprintf() seems working with \\0 inside of result", + sdslen(x) == 3 && memcmp(x,"a\0""b\0",4) == 0) + + { + sdsfree(x); + char etalon[1024*1024]; + for (size_t i = 0; i < sizeof(etalon); i++) { + etalon[i] = '0'; + } + x = sdscatprintf(sdsempty(),"%0*d",(int)sizeof(etalon),0); + test_cond("sdscatprintf() can print 1MB", + sdslen(x) == sizeof(etalon) && memcmp(x,etalon,sizeof(etalon)) == 0) + } + + sdsfree(x); + x = sdsnew("--"); + x = sdscatfmt(x, "Hello %s World %I,%I--", "Hi!", LLONG_MIN,LLONG_MAX); + test_cond("sdscatfmt() seems working in the base case", + sdslen(x) == 60 && + memcmp(x,"--Hello Hi! World -9223372036854775808," + "9223372036854775807--",60) == 0); + printf("[%s]\n",x); + + sdsfree(x); + x = sdsnew("--"); + x = sdscatfmt(x, "%u,%U--", UINT_MAX, ULLONG_MAX); + test_cond("sdscatfmt() seems working with unsigned numbers", + sdslen(x) == 35 && + memcmp(x,"--4294967295,18446744073709551615--",35) == 0); + + sdsfree(x); + x = sdsnew(" x "); + sdstrim(x," x"); + test_cond("sdstrim() works when all chars match", + sdslen(x) == 0); + + sdsfree(x); + x = sdsnew(" x "); + sdstrim(x," "); + test_cond("sdstrim() works when a single char remains", + sdslen(x) == 1 && x[0] == 'x'); + + sdsfree(x); + x = sdsnew("xxciaoyyy"); + sdstrim(x,"xy"); + test_cond("sdstrim() correctly trims characters", + sdslen(x) == 4 && memcmp(x,"ciao\0",5) == 0); + + y = sdsdup(x); + sdsrange(y,1,1); + test_cond("sdsrange(...,1,1)", + sdslen(y) == 1 && memcmp(y,"i\0",2) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,1,-1); + test_cond("sdsrange(...,1,-1)", + sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,-2,-1); + test_cond("sdsrange(...,-2,-1)", + sdslen(y) == 2 && memcmp(y,"ao\0",3) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,2,1); + test_cond("sdsrange(...,2,1)", + sdslen(y) == 0 && memcmp(y,"\0",1) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,1,100); + test_cond("sdsrange(...,1,100)", + sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,100,100); + test_cond("sdsrange(...,100,100)", + sdslen(y) == 0 && memcmp(y,"\0",1) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,4,6); + test_cond("sdsrange(...,4,6)", + sdslen(y) == 0 && memcmp(y,"\0",1) == 0); + + sdsfree(y); + y = sdsdup(x); + sdsrange(y,3,6); + test_cond("sdsrange(...,3,6)", + sdslen(y) == 1 && memcmp(y,"o\0",2) == 0); + + sdsfree(y); + sdsfree(x); + x = sdsnew("foo"); + y = sdsnew("foa"); + test_cond("sdscmp(foo,foa)", sdscmp(x,y) > 0); + + sdsfree(y); + sdsfree(x); + x = sdsnew("bar"); + y = sdsnew("bar"); + test_cond("sdscmp(bar,bar)", sdscmp(x,y) == 0); + + sdsfree(y); + sdsfree(x); + x = sdsnew("aar"); + y = sdsnew("bar"); + test_cond("sdscmp(bar,bar)", sdscmp(x,y) < 0); + + sdsfree(y); + sdsfree(x); + x = sdsnewlen("\a\n\0foo\r",7); + y = sdscatrepr(sdsempty(),x,sdslen(x)); + test_cond("sdscatrepr(...data...)", + memcmp(y,"\"\\a\\n\\x00foo\\r\"",15) == 0); + + { + char *p; + int step = 10, j, i; + + sdsfree(x); + sdsfree(y); + x = sdsnew("0"); + test_cond("sdsnew() free/len buffers", sdslen(x) == 1 && sdsavail(x) == 0); + + /* Run the test a few times in order to hit the first two + * SDS header types. */ + for (i = 0; i < 10; i++) { + int oldlen = sdslen(x); + x = sdsMakeRoomFor(x,step); + int type = x[-1]&SDS_TYPE_MASK; + + test_cond("sdsMakeRoomFor() len", sdslen(x) == oldlen); + if (type != SDS_TYPE_5) { + test_cond("sdsMakeRoomFor() free", sdsavail(x) >= step); + } + p = x+oldlen; + for (j = 0; j < step; j++) { + p[j] = 'A'+j; + } + sdsIncrLen(x,step); + } + test_cond("sdsMakeRoomFor() content", + memcmp("0ABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJABCDEFGHIJ",x,101) == 0); + test_cond("sdsMakeRoomFor() final length",sdslen(x)==101); + + sdsfree(x); + } + + x = sdsnew("0FoO1bar\n"); + sdstolower(x); + test_cond("sdstolower(...)", + memcmp(x,"0foo1bar\n\0",10) == 0); + + sdsfree(x); + + x = sdsnew("0FoO1bar\n"); + sdstoupper(x); + test_cond("sdstoupper(...)", + memcmp(x,"0FOO1BAR\n\0",10) == 0); + + sdsfree(x); + + /* Test sdsresize - extend */ + x = sdsnew("1234567890123456789012345678901234567890"); + x = sdsResize(x, 200); + test_cond("sdsrezie() expand len", sdslen(x) == 40); + test_cond("sdsrezie() expand strlen", strlen(x) == 40); + test_cond("sdsrezie() expand alloc", sdsalloc(x) == 200); + /* Test sdsresize - trim free space */ + x = sdsResize(x, 80); + test_cond("sdsrezie() shrink len", sdslen(x) == 40); + test_cond("sdsrezie() shrink strlen", strlen(x) == 40); + test_cond("sdsrezie() shrink alloc", sdsalloc(x) == 80); + /* Test sdsresize - crop used space */ + x = sdsResize(x, 30); + test_cond("sdsrezie() crop len", sdslen(x) == 30); + test_cond("sdsrezie() crop strlen", strlen(x) == 30); + test_cond("sdsrezie() crop alloc", sdsalloc(x) == 30); + /* Test sdsresize - extend to different class */ + x = sdsResize(x, 400); + test_cond("sdsrezie() expand len", sdslen(x) == 30); + test_cond("sdsrezie() expand strlen", strlen(x) == 30); + test_cond("sdsrezie() expand alloc", sdsalloc(x) == 400); + /* Test sdsresize - shrink to different class */ + x = sdsResize(x, 4); + test_cond("sdsrezie() crop len", sdslen(x) == 4); + test_cond("sdsrezie() crop strlen", strlen(x) == 4); + test_cond("sdsrezie() crop alloc", sdsalloc(x) == 4); + sdsfree(x); + } + test_report() + return 0; +} +#endif + +#ifdef SDS_TEST_MAIN +int main(void) { + return sdsTest(); +} +#endif diff --git a/library/sds.h b/library/sds.h new file mode 100644 index 0000000..65eb6e8 --- /dev/null +++ b/library/sds.h @@ -0,0 +1,155 @@ +/* SDSLib 2.3 -- A C dynamic strings library + * + * Copyright (c) 2006-2015, Salvatore Sanfilippo + * Copyright (c) 2015, Oran Agra + * Copyright (c) 2015, Redis Labs, Inc + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * * Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Redis nor the names of its contributors may be used + * to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __SDS_H +#define __SDS_H + +#define SDS_MAX_PREALLOC (1024*1024) +extern const char *SDS_NOINIT; + +#include +#include +#include + +typedef char *sds; + +/* Note: sdshdr5 is never used, we just access the flags byte directly. + * However is here to document the layout of type 5 SDS strings. */ +struct __attribute__ ((__packed__)) sdshdr5 { + unsigned char flags; /* 3 lsb of type, and 5 msb of string length */ + char buf[]; +}; +struct __attribute__ ((__packed__)) sdshdr8 { + uint8_t len; /* used */ + uint8_t alloc; /* excluding the header and null terminator */ + unsigned char flags; /* 3 lsb of type, 5 unused bits */ + char buf[]; +}; +struct __attribute__ ((__packed__)) sdshdr16 { + uint16_t len; /* used */ + uint16_t alloc; /* excluding the header and null terminator */ + unsigned char flags; /* 3 lsb of type, 5 unused bits */ + char buf[]; +}; +struct __attribute__ ((__packed__)) sdshdr32 { + uint32_t len; /* used */ + uint32_t alloc; /* excluding the header and null terminator */ + unsigned char flags; /* 3 lsb of type, 5 unused bits */ + char buf[]; +}; +struct __attribute__ ((__packed__)) sdshdr64 { + uint64_t len; /* used */ + uint64_t alloc; /* excluding the header and null terminator */ + unsigned char flags; /* 3 lsb of type, 5 unused bits */ + char buf[]; +}; + +#define SDS_TYPE_5 0 +#define SDS_TYPE_8 1 +#define SDS_TYPE_16 2 +#define SDS_TYPE_32 3 +#define SDS_TYPE_64 4 +#define SDS_TYPE_MASK 7 +#define SDS_TYPE_BITS 3 +#define SDS_HDR_VAR(T,s) struct sdshdr##T *sh = (void*)((s)-(sizeof(struct sdshdr##T))); +#define SDS_HDR(T,s) ((struct sdshdr##T *)((s)-(sizeof(struct sdshdr##T)))) +#define SDS_TYPE_5_LEN(f) ((f)>>SDS_TYPE_BITS) + +size_t sdslen(const sds s); +size_t sdsavail(const sds s); +void sdssetlen(sds s, size_t newlen); +void sdsinclen(sds s, size_t inc); +size_t sdsalloc(const sds s); +void sdssetalloc(sds s, size_t newlen); + +sds sdsnewlen(const void *init, size_t initlen); +sds sdsnew(const char *init); +sds sdsempty(void); +sds sdsdup(const sds s); +void sdsfree(sds s); +sds sdsgrowzero(sds s, size_t len); +sds sdscatlen(sds s, const void *t, size_t len); +sds sdscat(sds s, const char *t); +sds sdscatsds(sds s, const sds t); +sds sdscpylen(sds s, const char *t, size_t len); +sds sdscpy(sds s, const char *t); + +sds sdscatvprintf(sds s, const char *fmt, va_list ap); +#ifdef __GNUC__ +sds sdscatprintf(sds s, const char *fmt, ...) + __attribute__((format(printf, 2, 3))); +#else +sds sdscatprintf(sds s, const char *fmt, ...); +#endif + +sds sdscatfmt(sds s, char const *fmt, ...); +void sdstrim(sds s, const char *cset); +void sdssubstr(sds s, size_t start, size_t len); +void sdsrange(sds s, ssize_t start, ssize_t end); +void sdsupdatelen(sds s); +void sdsclear(sds s); +int sdscmp(const sds s1, const sds s2); +sds *sdssplitlen(const char *s, ssize_t len, const char *sep, int seplen, int *count); +void sdsfreesplitres(sds *tokens, int count); +void sdstolower(sds s); +void sdstoupper(sds s); +sds sdsfromlonglong(long long value); +sds sdscatrepr(sds s, const char *p, size_t len); +sds *sdssplitargs(const char *line, int *argc); +sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen); +sds sdsjoin(char **argv, int argc, char *sep); +sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen); +int sdsneedsrepr(const sds s); + +/* Low level functions exposed to the user API */ +sds sdsMakeRoomFor(sds s, size_t addlen); +void sdsIncrLen(sds s, ssize_t incr); +sds sdsRemoveFreeSpace(sds s); +sds sdsResize(sds s, size_t size); +size_t sdsAllocSize(sds s); +void *sdsAllocPtr(sds s); + +/* Export the allocator used by SDS to the program using SDS. + * Sometimes the program SDS is linked to, may use a different set of + * allocators, but may want to allocate or free things that SDS will + * respectively free or allocate. */ +void *sds_malloc(size_t size); +void *sds_realloc(void *ptr, size_t size); +void sds_free(void *ptr); + +#ifdef REDIS_TEST +int sdsTest(void); +#endif + +#undef inline + +#endif diff --git a/library/sdsalloc.h b/library/sdsalloc.h new file mode 100644 index 0000000..2eff946 --- /dev/null +++ b/library/sdsalloc.h @@ -0,0 +1,47 @@ +/* SDSLib 2.2 -- A C dynamic strings library + * + * Copyright (c) 2006-2015, Salvatore Sanfilippo + * Copyright (c) 2015, Oran Agra + * Copyright (c) 2015, Redis Labs, Inc + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * * Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Redis nor the names of its contributors may be used + * to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +/* SDS allocator selection. + * + * This file is used in order to change the SDS allocator at compile time. + * Just define the following defines to what you want to use. Also add + * the include of your alternate allocator if needed (not needed in order + * to use the default libc allocator). */ + +#ifndef __SDS_ALLOC_H__ +#define __SDS_ALLOC_H__ + +#define s_malloc malloc +#define s_realloc realloc +#define s_free free + +#endif diff --git a/source/TBSP_strings.inc b/source/TBSP_strings.inc new file mode 100644 index 0000000..7211c64 --- /dev/null +++ b/source/TBSP_strings.inc @@ -0,0 +1,122 @@ +const char * const TBSP_header = "\ +#include \n\ +#include \n\ +\n\ +#include \n\ +#ifdef __cplusplus\n\ +extern \"C\" {\n\ +#endif\n\ +extern const TSLanguage * tree_sitter_%s(void);\n\ +#ifdef __cplusplus\n\ +}\n\ +#endif\n\ +const TSLanguage * (*tblanguage_function)(void) = tree_sitter_%s;\n\ +\n\ +typedef struct {\n\ + const char * const string;\n\ + const int case_number;\n\ +} tbcase_t;\n\ +\n\ +// XXX better search algo\n\ +int determine_case(const tbcase_t * const ordered_array, const char * const string) {\n\ + const tbcase_t * c = ordered_array;\n\ + for (; c->string != NULL; c++) {\n\ + if (!strcmp(c->string, string)) { break; }\n\ + }\n\ +\n\ + return c->case_number;\n\ +}\n\ +\n\ +char * tbtext(const char * const code, TSNode node) {\n\ + int tblen = ts_node_end_byte(node) - ts_node_start_byte(node);\n\ + char * r = (char *)malloc(sizeof(char) * (tblen + 1));\n\ +\n\ + memcpy(r, code + ts_node_start_byte(node), tblen);\n\ + r[tblen] = '\\0';\n\ +\n\ + return r;\n\ +}\n\ +\n\ +#define GET_TBTEXT tbtext(code, current_node)\n\ +"; + +const char * const TBSP_case = "\ + (tbcase_t) { .string = \"%s\", .case_number = %d },\n\ +"; + +const char * const TBSP_traverse_top = "\ +int tbtraverse(const char * const code) {\n\ + // init\n\ + TSParser * parser;\n\ + TSTree * tree;\n\ + TSTreeCursor cursor;\n\ + TSNode current_node;\n\ +\n\ + int tb_case;\n\ +\n\ + parser = ts_parser_new();\n\ +\n\ + ts_parser_set_language(parser, tblanguage_function());\n\ +\n\ + tree = ts_parser_parse_string(parser, NULL, code, strlen(code));\n\ + cursor = ts_tree_cursor_new(ts_tree_root_node(tree));\n\ + current_node = ts_tree_root_node(tree);\n\ +\n\ + const tbcase_t * current_cases = tb_enter_cases;\n\ +\n\ + // meat\n\ + while (true) {\n\ + current_node = ts_tree_cursor_current_node(&cursor);\n\ +\n\ + tb_case = determine_case(current_cases, ts_node_type(current_node));\n\ +\n\ + // XXX INJECTION\n\ + #if defined(TBDEBUG) && TBDEBUG == 1\n\ + puts(ts_node_string(current_node));\n\ + #endif\n\ + switch (tb_case) {\n\ +"; + +const char * const TBSP_traverse_bottom = "\ + default: { ; } break;\n\ + }\n\ +\n\ + if (ts_node_child_count(current_node)\n\ + && current_cases == tb_enter_cases) {\n\ + ts_tree_cursor_goto_first_child(&cursor);\n\ + continue;\n\ + }\n\ +\n\ + logic:\n\ + if (!ts_node_is_null(ts_node_next_sibling(current_node))) {\n\ + if (current_cases == tb_enter_cases) {\n\ + current_cases = tb_leave_cases;\n\ + continue;\n\ + } else {\n\ + ts_tree_cursor_goto_next_sibling(&cursor);\n\ + current_cases = tb_enter_cases;\n\ + continue;\n\ + }\n\ + }\n\ +\n\ + if (current_cases == tb_enter_cases) {\n\ + current_cases = tb_leave_cases;\n\ + continue;\n\ + }\n\ +\n\ + if (ts_tree_cursor_goto_parent(&cursor)) {\n\ + current_cases = tb_enter_cases;\n\ + goto logic;\n\ + }\n\ +\n\ + break;\n\ + }\n\ +\n\ + // deinit\n\ + ts_tree_delete(tree);\n\ + ts_parser_delete(parser);\n\ + ts_tree_cursor_delete(&cursor);\n\ +\n\ + return 0;\n\ +}\n\ +"; diff --git a/source/tbc.c b/source/tbc.c new file mode 100644 index 0000000..8aed421 --- /dev/null +++ b/source/tbc.c @@ -0,0 +1,116 @@ +#include +#include + +#include +extern const TSLanguage * tree_sitter_c(void); + +typedef struct { + const char * const string; + const int case_number; +} tbcase_t; + +const tbcase_t tb_enter_cases[] = { + (tbcase_t) { .string = "function_definition", .case_number = 1 }, + (tbcase_t) { .string = "number_literal", .case_number = 2 }, + (tbcase_t) { .string = NULL, .case_number = 0 }, +}; + +const tbcase_t tb_leave_cases[] = { + (tbcase_t) { .string = "function_definition", .case_number = 3 }, + (tbcase_t) { .string = NULL, .case_number = 0 }, +}; + +// XXX better search algo +int determine_case(const tbcase_t * const ordered_array, const char * const string) { + const tbcase_t * c = ordered_array; + for (; c->string != NULL; c++) { + if (!strcmp(c->string, string)) { break; } + } + + return c->case_number; +} + +char * tbtext(const char * const code, TSNode node) { + int tblen = ts_node_end_byte(node) - ts_node_start_byte(node); + char * r = (char *)malloc(sizeof(char) * (tblen + 1)); + + memcpy(r, code + ts_node_start_byte(node), tblen); + r[tblen] = '\0'; + + return r; +} + +#define GET_TBTEXT tbtext(code, current_node) + +int tbtraverse(const char * const code) { + // init + TSParser * parser; + TSTree * tree; + TSTreeCursor cursor; + TSNode current_node; + + int tb_case; + + parser = ts_parser_new(); + + ts_parser_set_language(parser, tree_sitter_c()); + + tree = ts_parser_parse_string(parser, NULL, code, strlen(code)); + cursor = ts_tree_cursor_new(ts_tree_root_node(tree)); + current_node = ts_tree_root_node(tree); + + // meat + while (true) { + current_node = ts_tree_cursor_current_node(&cursor); + + tb_case = determine_case(tb_enter_cases, ts_node_type(current_node)); + + // XXX INJECTION + eval: + switch (tb_case) { + case 1: { + puts("ack"); + char * mytbtext = GET_TBTEXT; + puts(mytbtext); + free(mytbtext); + } break; + case 2: { + puts("++"); + } break; + case 3: { + puts("^^df"); + } break; + default: { ; } break; + } + + if (ts_tree_cursor_goto_first_child(&cursor) + || ts_tree_cursor_goto_next_sibling(&cursor)) { + continue; + } + + while (ts_tree_cursor_goto_parent(&cursor)) { + current_node = ts_tree_cursor_current_node(&cursor); + if (ts_tree_cursor_goto_next_sibling(&cursor)) { + tb_case = determine_case(tb_leave_cases, ts_node_type(current_node)); + goto eval; + } + } + + break; + } + + // deinit + ts_tree_delete(tree); + ts_parser_delete(parser); + ts_tree_cursor_delete(&cursor); + + return 0; +} + + +// @BAKE gcc $@ $(pkg-config --cflags --libs tree-sitter tree-sitter-c) -ggdb + +signed main() { + tbtraverse("int main() { return 0; }"); +} + diff --git a/source/tbc.cpp b/source/tbc.cpp index bcc8662..43a4ed6 100644 --- a/source/tbc.cpp +++ b/source/tbc.cpp @@ -1,8 +1,33 @@ #include #include -extern "C" { - #include - extern const TSLanguage * tree_sitter_c(void); + +#include +extern const TSLanguage * tree_sitter_c(void); + +typedef struct { + const char * const string; + const int case_number; +} tbcase_t; + +const tbcase_t tb_enter_cases[] = { + (tbcase_t) { .string = "function_definition", .case_number = 1 }, + (tbcase_t) { .string = "number_literal", .case_number = 2 }, + (tbcase_t) { .string = NULL, .case_number = 0 }, +}; + +const tbcase_t tb_leave_cases[] = { + (tbcase_t) { .string = "function_definition", .case_number = 3 }, + (tbcase_t) { .string = NULL, .case_number = 0 }, +}; + +// XXX better search algo +int determine_case(tbcase_t * ordered_array, const char * const string) { + tbcase_t * c; + for (; c->string != NULL; c++) { + if (!strcmp(c->string, string)) { break; } + } + + return c->case_number; } int tbtraverse(const char * const code) { @@ -13,6 +38,8 @@ int tbtraverse(const char * const code) { TSNode current_node; TSNode previous_node; + int tb_case; + parser = ts_parser_new(); ts_parser_set_language(parser, tree_sitter_c()); @@ -22,71 +49,51 @@ int tbtraverse(const char * const code) { current_node = ts_tree_root_node(tree); // meat - do { + while (true) { current_node = ts_tree_cursor_current_node(&cursor); - const char * previous_node_type = NULL; - int tblen = ts_node_end_byte(current_node) - ts_node_start_byte(current_node); char * tbtext = (char *)malloc(sizeof(char) * (tblen + 1)); memcpy(tbtext, code + ts_node_start_byte(current_node), tblen); tbtext[tblen] = '\0'; + tb_case = determine_case(tb_enter_cases, ts_node_type(current_node)); + // XXX INJECTION - - if (!strcmp("function_definition", ts_node_type(current_node))) { - - puts("ack"); - puts(tbtext); - - goto end; - } - - - if (!strcmp("number_literal", ts_node_type(current_node))) { - - puts("++"); - - goto end; - } - - - - end: - free(tbtext); - } while ([&] { - bool r = false; - previous_node = current_node; - - if (ts_tree_cursor_goto_first_child(&cursor) - || ts_tree_cursor_goto_next_sibling(&cursor)) { - r = true; - goto eval; - } - - while (ts_tree_cursor_goto_parent(&cursor)) { - if (!strcmp(ts_node_type(current_node), "translation_unit")) { - r = false; - break; - } - - if (ts_tree_cursor_goto_next_sibling(&cursor)) { - r = true; - } - - eval: - if (!strcmp("function_definition", ts_node_type(previous_node))) { + eval: + switch (tb_case) { + case 1: { + puts("ack"); + puts(tbtext); + } break; + case 2: { + puts("++"); + } break; + case 3: { puts("^^df"); - - goto end; - } - - end: - if (r) { break; } + } break; + [[likely]] default: { ; } break; } - return r; - }()); + free(tbtext); + + if (ts_tree_cursor_goto_first_child(&cursor) + || ts_tree_cursor_goto_next_sibling(&cursor)) { + current_node = ts_tree_cursor_current_node(&cursor); + tb_case = determine_case(tb_leave_cases, ts_node_type); + goto eval; + } + + while (ts_tree_cursor_goto_parent(&cursor)) { + current_node = ts_tree_cursor_current_node(&cursor); + if (ts_tree_cursor_goto_next_sibling(&cursor)) { + tb_case = determine_case(tb_leave_cases, ts_node_type); + goto eval; + } + } + + break; + } // deinit ts_tree_delete(tree); @@ -102,4 +109,3 @@ int tbtraverse(const char * const code) { signed main() { tbtraverse("int main() { return 0; }"); } - diff --git a/source/tbsp.c b/source/tbsp.c new file mode 100644 index 0000000..70d7eb3 --- /dev/null +++ b/source/tbsp.c @@ -0,0 +1,112 @@ +#define _GNU_SOURCE +#include + +#include "tbsp.yy.h" +#include "tbsp.tab.h" + +// XXX i am so desperate for #embed, you would not believe +#include "TBSP_strings.inc" + +extern int tbsp_yy_init(void); +extern int tbsp_yy_deinit(void); + +char * language = NULL; +char * verbatim = NULL; +char * top = NULL; + +void put_rule_table(const char * const name, rule_type_t type_mask) { + char * sprint_buffer; + int sprint_r; + (void)sprint_r; + fputs("const tbcase_t tb_", yyout); + fputs(name, yyout); + fputs("[] = {\n", yyout); + for (int i = 0; i < kv_size(rules); i++) { + if (!(kv_A(rules, i).type & type_mask)) { continue; } + sprint_r = asprintf(&sprint_buffer, + TBSP_case, + kv_A(rules, i).string, + kv_A(rules, i).target + ); + fputs(sprint_buffer, yyout); + free(sprint_buffer); + } + fputs(" (tbcase_t) { .string = NULL, .case_number = 0 },\n", yyout); + fputs("};\n\n", yyout); +} + +signed main(const int argc, const char * const * const argv) { + #ifdef DEBUG + yydebug = 1; + #endif + + if (argc < 2) { + printf("%s ", argv[0]); + } + + tbsp_yy_init(); + tbsp_tab_init(); + + yyin = fopen(argv[1], "r"); + if (!yyin) { + puts("Failed to open file"); + return 1; + } + + //yyout = fopen("tbsp.c", "w"); + yyout = stdout; + + int yyparse_r = yyparse(); + if (yyparse_r) { + return 1; + } + + char * sprint_buffer; + int sprint_r; + (void)sprint_r; + + // Header + sprint_r = asprintf(&sprint_buffer, TBSP_header, language, language); + fputs(sprint_buffer, yyout); + free(sprint_buffer); + + // Definition section + fputs(top, yyout); + + // Rule section + put_rule_table("enter_cases", ENTER_RULE); + put_rule_table("leave_cases", LEAVE_RULE); + + fputs(TBSP_traverse_top, yyout); + for (int i = 0; i < kv_size(rules); i++) { + const char * const case_string = "\ + case %d: {\n\ + %s\n\ + } break;\n\ + "; + sprint_r = asprintf(&sprint_buffer, + case_string, + kv_A(rules, i).target, + kv_A(rules, i).code + ); + fputs(sprint_buffer, yyout); + free(sprint_buffer); + } + fputs(TBSP_traverse_bottom, yyout); + + // Code section + fputs(verbatim, yyout); + + // Deinit + for (int i = 0; i < kv_size(rules); i++) { + free(kv_A(rules, i).string); + free(kv_A(rules, i).code); + } + + tbsp_yy_deinit(); + free(verbatim); + free(language); + free(top); + + return 0; +} diff --git a/source/tbsp.l b/source/tbsp.l new file mode 100644 index 0000000..6ef64c5 --- /dev/null +++ b/source/tbsp.l @@ -0,0 +1,94 @@ +%{ + #include + #include "tbsp.tab.h" + + int code_nesting = 0; + + int code_caller; + + sds buffer; +%} + +identifier [a-zA-z][-a-zA-z0-9_]* + +%x IN_DEFINITION_SECTION IN_RULE_SECTION IN_CODE_SECTION +%x IN_CODE + +%option nodefault +%option noyywrap +%% +. { yyless(0); BEGIN IN_DEFINITION_SECTION; } + +{ +\%top[[:space:]]+\{ { + code_caller = IN_DEFINITION_SECTION; + BEGIN IN_CODE; + return TOP; + } +\%language[[:space:]] { + return LANGUAGE; + } +{identifier} { + yylval.strval = strdup(yytext); + return IDENTIFIER; + } +[[:space:]] { ; } +\%\% { + BEGIN IN_RULE_SECTION; + return SEPARATOR; + } +} + +{ +\{ { + code_caller = IN_RULE_SECTION; + BEGIN IN_CODE; + } +\} { ; } +[[:space:]]* { ; } +enter[[:space:]] { return ENTER; } +leave[[:space:]] { return LEAVE; } +{identifier} { + yylval.strval = strdup(yytext); + return IDENTIFIER; + } +\%\% { + BEGIN IN_CODE_SECTION; + return SEPARATOR; + } +} + +{ +\{ { ++code_nesting; } +\} { + if (!code_nesting) { + yylval.strval = strdup(buffer); + sdsclear(buffer); + BEGIN code_caller; + return CODE_BLOB; + } + + --code_nesting; + ; + } +.|\n { buffer = sdscat(buffer, yytext); } +} + +{ +(.|\n)* { + yylval.strval = strdup(yytext); + BEGIN IN_DEFINITION_SECTION; + return CODE_BLOB; + } +} +%% + +int tbsp_yy_init(void) { + buffer = sdsnew(""); + return 0; +} + +int tbsp_yy_deinit(void) { + sdsfree(buffer); + return 0; +} diff --git a/source/tbsp.y b/source/tbsp.y new file mode 100644 index 0000000..5c221fc --- /dev/null +++ b/source/tbsp.y @@ -0,0 +1,126 @@ +%{ + #include "tbsp.yy.h" + + void yyerror([[maybe_unused]] const char * const s); + + extern char * language; + extern char * top; + extern char * verbatim; + + int target_counter = 1; + + #define COMA , +%} +%code requires { + typedef enum { + ENTER_RULE = 0b0001, + LEAVE_RULE = 0b0010, + } rule_type_t; + + typedef struct { + rule_type_t type; + int target; + char * string; + char * code; + } rule_t; + + #include + typedef kvec_t(rule_t) rule_vector_t; + extern rule_vector_t rules; +} +%code provides { + void tbsp_tab_init(void); + void tbsp_tab_deinit(void); +} +%union{ + char * strval; + rule_type_t ruleval; +} +%token SEPARATOR +%token TOP LANGUAGE +%token ENTER LEAVE +%token IDENTIFIER CODE_BLOB +%type rule_type +%type rule_selector +%% +document + : %empty + | definition_section SEPARATOR rule_section SEPARATOR code_section + ; + +definition_section + : %empty + | top definition_section + | language definition_section + ; + +top + : TOP CODE_BLOB { + if (top) { + puts("error: reee"); + return 1; + } + top = $2; + } + ; + +language + : LANGUAGE IDENTIFIER { + language = $2; + } + ; + +rule_section + : %empty + | rule rule_section + ; + +rule + : rule_type rule_selector CODE_BLOB { + kv_push(rule_t, rules, (rule_t) { + .type = $1 COMA + .target = target_counter COMA + .string = $2 COMA + .code = $3 COMA + }); + ++target_counter; + } + ; + +rule_type + : %empty { $$ = 0; } + | ENTER rule_type { $$ |= ENTER_RULE; } + | LEAVE rule_type { $$ |= LEAVE_RULE; } + ; + +rule_selector + : IDENTIFIER { $$ = $1; } + ; + + +code_section + : CODE_BLOB { + verbatim = $1; + } + ; + +%% + +rule_vector_t rules; + +void yyerror(const char * const s) { + puts("yyerror"); +} + +void tbsp_tab_init(void) { + kv_init(rules); +} + +void tbsp_tab_deinit(void) { + for (int i = 0; i < kv_size(rules); i++) { + free(kv_A(rules, i).string); + free(kv_A(rules, i).code); + } + + kv_destroy(rules); +}