1
0
forked from GitHub/gf-core

Merge branch 'master' into c-runtime

This commit is contained in:
krangelov
2021-07-30 11:20:04 +02:00
211 changed files with 7161 additions and 58549 deletions
+5 -2
View File
@@ -14,6 +14,9 @@ For Linux users
You will need the packages: autoconf, automake, libtool, make
- On Ubuntu: $ apt-get install autotools-dev
- On Fedora: $ dnf install autoconf automake libtool
The compilation steps are:
$ autoreconf -i
@@ -28,7 +31,7 @@ For Mac OSX users
The following is what I did to make it work on MacOSX 10.8:
- Install XCode and XCode command line tools
- Install Homebrew: http://mxcl.github.com/homebrew/
- Install Homebrew: https://brew.sh
$ brew install automake autoconf libtool
$ glibtoolize
@@ -49,7 +52,7 @@ For Windows users
After the installation, don't forget to fix the fstab file. See here:
http://www.mingw.org/wiki/Getting_Started
- From the MSYS shell (c:/MinGW/msys/1.0/msys.bat) go to the directory
- From the MSYS shell (c:/MinGW/msys/1.0/msys.bat) go to the directory
which contains the INSTALL file and do:
$ autoreconf -i
+3 -13
View File
@@ -1,7 +1,7 @@
lib_LTLIBRARIES = libgu.la libpgf.la libsg.la
lib_LTLIBRARIES = libgu.la libpgf.la
pkgconfigdir = $(libdir)/pkgconfig
pkgconfig_DATA = libgu.pc libpgf.pc libsg.pc
pkgconfig_DATA = libgu.pc libpgf.pc
configincludedir = $(libdir)/libgu/include
@@ -37,10 +37,6 @@ pgfinclude_HEADERS = \
pgf/pgf.h \
pgf/data.h
sgincludedir=$(includedir)/sg
sginclude_HEADERS = \
sg/sg.h
libgu_la_SOURCES = \
gu/assert.c \
gu/bits.c \
@@ -92,11 +88,6 @@ libpgf_la_SOURCES = \
libpgf_la_LDFLAGS = "-no-undefined"
libpgf_la_LIBADD = libgu.la
libsg_la_SOURCES = \
sg/sqlite3Btree.c \
sg/sg.c
libsg_la_LIBADD = libgu.la libpgf.la
bin_PROGRAMS =
AUTOMAKE_OPTIONS = foreign subdir-objects dist-bzip2
@@ -104,5 +95,4 @@ ACLOCAL_AMFLAGS = -I m4
EXTRA_DIST = \
libgu.pc.in \
libpgf.pc.in \
libsg.pc.in
libpgf.pc.in
-1
View File
@@ -58,7 +58,6 @@ AC_CONFIG_LINKS(pgf/lightning/asm.h:$cpu_dir/asm.h dnl
AC_CONFIG_FILES([Makefile
libgu.pc
libpgf.pc
libsg.pc
])
AC_OUTPUT
+9 -6
View File
@@ -322,7 +322,7 @@ gu_map_iter(GuMap* map, GuMapItor* itor, GuExn* err)
}
GU_API bool
gu_map_next(GuMap* map, size_t* pi, void** pkey, void* pvalue)
gu_map_next(GuMap* map, size_t* pi, void* pkey, void* pvalue)
{
while (*pi < map->data.n_entries) {
if (gu_map_entry_is_free(map, &map->data, *pi)) {
@@ -330,14 +330,17 @@ gu_map_next(GuMap* map, size_t* pi, void** pkey, void* pvalue)
continue;
}
*pkey = &map->data.keys[*pi * map->key_size];
if (map->hasher == gu_addr_hasher) {
*pkey = *(void**) *pkey;
*((void**) pkey) = *((void**) &map->data.keys[*pi * sizeof(void*)]);
} else if (map->hasher == gu_word_hasher) {
*((GuWord*) pkey) = *((GuWord*) &map->data.keys[*pi * sizeof(GuWord)]);
} else if (map->hasher == gu_string_hasher) {
*pkey = *(void**) *pkey;
}
*((GuString*) pkey) = *((GuString*) &map->data.keys[*pi * sizeof(GuString)]);
} else {
memcpy(pkey, &map->data.keys[*pi * map->key_size], map->key_size);
}
memcpy(pvalue, &map->data.values[*pi * map->cell_size],
memcpy(pvalue, &map->data.values[*pi * map->cell_size],
map->value_size);
(*pi)++;
+1 -1
View File
@@ -75,7 +75,7 @@ GU_API_DECL void
gu_map_iter(GuMap* ht, GuMapItor* itor, GuExn* err);
GU_API bool
gu_map_next(GuMap* map, size_t* pi, void** pkey, void* pvalue);
gu_map_next(GuMap* map, size_t* pi, void* pkey, void* pvalue);
typedef GuMap GuIntMap;
+3
View File
@@ -0,0 +1,3 @@
bash setup.sh configure
bash setup.sh build
bash setup.sh install
-10
View File
@@ -1,10 +0,0 @@
prefix=@prefix@
exec_prefix=@exec_prefix@
libdir=@libdir@
includedir=@includedir@
Name: libsg
Description: Semantic Graph library
Version: @VERSION@
Libs: -L${libdir} -lsg -lpgf
Cflags: -I${includedir}
+2 -2
View File
@@ -142,14 +142,14 @@ pgf_aligner_lzn_symbol_token(PgfLinFuncs** funcs, PgfToken tok)
}
static void
pgf_aligner_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lindex, PgfCId fun)
pgf_aligner_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfAlignerLin* alin = gu_container(funcs, PgfAlignerLin, funcs);
gu_buf_push(alin->parent_stack, int, fid);
}
static void
pgf_aligner_lzn_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lindex, PgfCId fun)
pgf_aligner_lzn_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfAlignerLin* alin = gu_container(funcs, PgfAlignerLin, funcs);
gu_buf_pop(alin->parent_stack, int);
+2 -1
View File
@@ -322,7 +322,8 @@ typedef struct PgfProductionCoerce
typedef struct {
PgfExprProb *ep;
GuSeq* lins;
size_t n_lins;
PgfSymbols* lins[];
} PgfProductionExtern;
typedef struct {
+162 -101
View File
@@ -953,94 +953,6 @@ pgf_read_expr(GuIn* in, GuPool* pool, GuPool* tmp_pool, GuExn* err)
return expr;
}
PGF_API int
pgf_read_expr_tuple(GuIn* in,
size_t n_exprs, PgfExpr exprs[],
GuPool* pool, GuExn* err)
{
GuPool* tmp_pool = gu_new_pool();
PgfExprParser* parser =
pgf_new_parser(in, pgf_expr_parser_in_getc, pool, tmp_pool, err);
if (parser->token_tag != PGF_TOKEN_LTRIANGLE)
goto fail;
pgf_expr_parser_token(parser, false);
for (size_t i = 0; i < n_exprs; i++) {
if (i > 0) {
if (parser->token_tag != PGF_TOKEN_COMMA)
goto fail;
pgf_expr_parser_token(parser, false);
}
exprs[i] = pgf_expr_parser_expr(parser, false);
if (gu_variant_is_null(exprs[i]))
goto fail;
}
if (parser->token_tag != PGF_TOKEN_RTRIANGLE)
goto fail;
pgf_expr_parser_token(parser, false);
if (parser->token_tag != PGF_TOKEN_EOF)
goto fail;
gu_pool_free(tmp_pool);
return 1;
fail:
gu_pool_free(tmp_pool);
return 0;
}
PGF_API GuSeq*
pgf_read_expr_matrix(GuIn* in,
size_t n_exprs,
GuPool* pool, GuExn* err)
{
GuPool* tmp_pool = gu_new_pool();
PgfExprParser* parser =
pgf_new_parser(in, pgf_expr_parser_in_getc, pool, tmp_pool, err);
if (parser->token_tag != PGF_TOKEN_LTRIANGLE)
goto fail;
pgf_expr_parser_token(parser, false);
GuBuf* buf = gu_new_buf(PgfExpr, pool);
if (parser->token_tag != PGF_TOKEN_RTRIANGLE) {
for (;;) {
PgfExpr* exprs = gu_buf_extend_n(buf, n_exprs);
for (size_t i = 0; i < n_exprs; i++) {
if (i > 0) {
if (parser->token_tag != PGF_TOKEN_COMMA)
goto fail;
pgf_expr_parser_token(parser, false);
}
exprs[i] = pgf_expr_parser_expr(parser, false);
if (gu_variant_is_null(exprs[i]))
goto fail;
}
if (parser->token_tag != PGF_TOKEN_SEMI)
break;
pgf_expr_parser_token(parser, false);
}
if (parser->token_tag != PGF_TOKEN_RTRIANGLE)
goto fail;
}
pgf_expr_parser_token(parser, false);
if (parser->token_tag != PGF_TOKEN_EOF)
goto fail;
gu_pool_free(tmp_pool);
return gu_buf_data_seq(buf);
fail:
gu_pool_free(tmp_pool);
return NULL;
}
PGF_API PgfType*
pgf_read_type(GuIn* in, GuPool* pool, GuPool* tmp_pool, GuExn* err)
{
@@ -1758,19 +1670,6 @@ pgf_print_context(PgfHypos *hypos, PgfPrintContext* ctxt,
}
}
PGF_API void
pgf_print_expr_tuple(size_t n_exprs, PgfExpr exprs[], PgfPrintContext* ctxt,
GuOut* out, GuExn* err)
{
gu_putc('<', out, err);
for (size_t i = 0; i < n_exprs; i++) {
if (i > 0)
gu_putc(',', out, err);
pgf_print_expr(exprs[i], ctxt, 0, out, err);
}
gu_putc('>', out, err);
}
PGF_API bool
pgf_type_eq(PgfType* t1, PgfType* t2)
{
@@ -1806,6 +1705,168 @@ pgf_type_eq(PgfType* t1, PgfType* t2)
return true;
}
PGF_API PgfLiteral
pgf_clone_literal(PgfLiteral lit, GuPool* pool)
{
PgfLiteral new_lit = gu_null_variant;
GuVariantInfo inf = gu_variant_open(lit);
switch (inf.tag) {
case PGF_LITERAL_STR: {
PgfLiteralStr* lit_str = inf.data;
PgfLiteralStr* new_lit_str =
gu_new_flex_variant(PGF_LITERAL_STR,
PgfLiteralStr,
val, strlen(lit_str->val)+1,
&new_lit, pool);
strcpy(new_lit_str->val, lit_str->val);
break;
}
case PGF_LITERAL_INT: {
PgfLiteralInt *lit_int = inf.data;
PgfLiteralInt *new_lit_int =
gu_new_variant(PGF_LITERAL_INT,
PgfLiteralInt,
&new_lit, pool);
new_lit_int->val = lit_int->val;
break;
}
case PGF_LITERAL_FLT: {
PgfLiteralFlt *lit_flt = inf.data;
PgfLiteralFlt *new_lit_flt =
gu_new_variant(PGF_LITERAL_FLT,
PgfLiteralFlt,
&new_lit, pool);
new_lit_flt->val = lit_flt->val;
break;
}
default:
gu_impossible();
}
return new_lit;
}
PGF_API PgfExpr
pgf_clone_expr(PgfExpr expr, GuPool* pool)
{
PgfExpr new_expr = gu_null_variant;
GuVariantInfo inf = gu_variant_open(expr);
switch (inf.tag) {
case PGF_EXPR_ABS: {
PgfExprAbs* abs = inf.data;
PgfExprAbs* new_abs =
gu_new_variant(PGF_EXPR_ABS,
PgfExprAbs,
&new_expr, pool);
new_abs->bind_type = abs->bind_type;
new_abs->id = gu_string_copy(abs->id, pool);
new_abs->body = pgf_clone_expr(abs->body,pool);
break;
}
case PGF_EXPR_APP: {
PgfExprApp* app = inf.data;
PgfExprApp* new_app =
gu_new_variant(PGF_EXPR_APP,
PgfExprApp,
&new_expr, pool);
new_app->fun = pgf_clone_expr(app->fun, pool);
new_app->arg = pgf_clone_expr(app->arg, pool);
break;
}
case PGF_EXPR_LIT: {
PgfExprLit* lit = inf.data;
PgfExprLit* new_lit =
gu_new_variant(PGF_EXPR_LIT,
PgfExprLit,
&new_expr, pool);
new_lit->lit = pgf_clone_literal(lit->lit, pool);
break;
}
case PGF_EXPR_META: {
PgfExprMeta* meta = inf.data;
PgfExprMeta* new_meta =
gu_new_variant(PGF_EXPR_META,
PgfExprMeta,
&new_expr, pool);
new_meta->id = meta->id;
break;
}
case PGF_EXPR_FUN: {
PgfExprFun* fun = inf.data;
PgfExprFun* new_fun =
gu_new_flex_variant(PGF_EXPR_FUN,
PgfExprFun,
fun, strlen(fun->fun)+1,
&new_expr, pool);
strcpy(new_fun->fun, fun->fun);
break;
}
case PGF_EXPR_VAR: {
PgfExprVar* var = inf.data;
PgfExprVar* new_var =
gu_new_variant(PGF_EXPR_VAR,
PgfExprVar,
&new_expr, pool);
new_var->var = var->var;
break;
}
case PGF_EXPR_TYPED: {
PgfExprTyped* typed = inf.data;
PgfExprTyped *new_typed =
gu_new_variant(PGF_EXPR_TYPED,
PgfExprTyped,
&new_expr, pool);
new_typed->expr = pgf_clone_expr(typed->expr, pool);
new_typed->type = pgf_clone_type(typed->type, pool);
break;
}
case PGF_EXPR_IMPL_ARG: {
PgfExprImplArg* impl = inf.data;
PgfExprImplArg *new_impl =
gu_new_variant(PGF_EXPR_IMPL_ARG,
PgfExprImplArg,
&new_expr, pool);
new_impl->expr = pgf_clone_expr(impl->expr, pool);
break;
}
default:
gu_impossible();
}
return new_expr;
}
PGF_API PgfType*
pgf_clone_type(PgfType* type, GuPool* pool)
{
PgfType* new_type =
gu_new_flex(pool, PgfType, exprs, type->n_exprs);
size_t n_hypos = gu_seq_length(type->hypos);
new_type->hypos = gu_new_seq(PgfHypo, n_hypos, pool);
for (size_t i = 0; i < n_hypos; i++) {
PgfHypo* hypo = gu_seq_index(type->hypos, PgfHypo, i);
PgfHypo* new_hypo = gu_seq_index(new_type->hypos, PgfHypo, i);
new_hypo->bind_type = hypo->bind_type;
new_hypo->cid = gu_string_copy(hypo->cid, pool);
new_hypo->type = pgf_clone_type(hypo->type, pool);
}
new_type->cid = gu_string_copy(type->cid, pool);
new_type->n_exprs = type->n_exprs;
for (size_t i = 0; i < new_type->n_exprs; i++) {
new_type->exprs[i] = pgf_clone_expr(type->exprs[i], pool);
}
return new_type;
}
PGF_API prob_t
pgf_compute_tree_probability(PgfPGF *gr, PgfExpr expr)
{
+8 -12
View File
@@ -171,15 +171,6 @@ pgf_expr_unmeta(PgfExpr expr);
PGF_API_DECL PgfExpr
pgf_read_expr(GuIn* in, GuPool* pool, GuPool* tmp_pool, GuExn* err);
PGF_API_DECL int
pgf_read_expr_tuple(GuIn* in,
size_t n_exprs, PgfExpr exprs[],
GuPool* pool, GuExn* err);
PGF_API_DECL GuSeq*
pgf_read_expr_matrix(GuIn* in, size_t n_exprs,
GuPool* pool, GuExn* err);
PGF_API_DECL PgfType*
pgf_read_type(GuIn* in, GuPool* pool, GuPool* tmp_pool, GuExn* err);
@@ -239,9 +230,14 @@ PGF_API_DECL void
pgf_print_context(PgfHypos *hypos, PgfPrintContext* ctxt,
GuOut *out, GuExn *err);
PGF_API_DECL void
pgf_print_expr_tuple(size_t n_exprs, PgfExpr exprs[], PgfPrintContext* ctxt,
GuOut* out, GuExn* err);
PGF_API PgfLiteral
pgf_clone_literal(PgfLiteral lit, GuPool* pool);
PGF_API PgfExpr
pgf_clone_expr(PgfExpr expr, GuPool* pool);
PGF_API PgfType*
pgf_clone_type(PgfType* type, GuPool* pool);
PGF_API_DECL prob_t
pgf_compute_tree_probability(PgfPGF *gr, PgfExpr expr);
+2 -2
View File
@@ -155,7 +155,7 @@ pgf_bracket_lzn_symbol_token(PgfLinFuncs** funcs, PgfToken tok)
}
static void
pgf_bracket_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lindex, PgfCId fun)
pgf_bracket_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfBracketLznState* state = gu_container(funcs, PgfBracketLznState, funcs);
@@ -192,7 +192,7 @@ pgf_bracket_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t li
}
static void
pgf_bracket_lzn_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lindex, PgfCId fun)
pgf_bracket_lzn_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfBracketLznState* state = gu_container(funcs, PgfBracketLznState, funcs);
+21 -21
View File
@@ -628,7 +628,7 @@ typedef struct {
PgfLzrCachedTag tag;
PgfCId cat;
int fid;
int lin_idx;
GuString ann;
PgfCId fun;
} PgfLzrCached;
@@ -666,7 +666,7 @@ pgf_lzr_cache_flush(PgfLzrCache* cache, PgfSymbols* form)
cache->lzr->funcs,
event->cat,
event->fid,
event->lin_idx,
event->ann,
event->fun);
}
break;
@@ -676,7 +676,7 @@ pgf_lzr_cache_flush(PgfLzrCache* cache, PgfSymbols* form)
cache->lzr->funcs,
event->cat,
event->fid,
event->lin_idx,
event->ann,
event->fun);
}
break;
@@ -731,27 +731,27 @@ found:
}
static void
pgf_lzr_cache_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin_idx, PgfCId fun)
pgf_lzr_cache_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfLzrCache* cache = gu_container(funcs, PgfLzrCache, funcs);
PgfLzrCached* event = gu_buf_extend(cache->events);
event->tag = PGF_CACHED_BEGIN;
event->cat = cat;
event->fid = fid;
event->lin_idx = lin_idx;
event->fun = fun;
event->tag = PGF_CACHED_BEGIN;
event->cat = cat;
event->fid = fid;
event->ann = ann;
event->fun = fun;
}
static void
pgf_lzr_cache_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin_idx, PgfCId fun)
pgf_lzr_cache_end_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfLzrCache* cache = gu_container(funcs, PgfLzrCache, funcs);
PgfLzrCached* event = gu_buf_extend(cache->events);
event->tag = PGF_CACHED_END;
event->cat = cat;
event->fid = fid;
event->lin_idx = lin_idx;
event->fun = fun;
event->tag = PGF_CACHED_END;
event->cat = cat;
event->fid = fid;
event->ann = ann;
event->fun = fun;
}
static void
@@ -939,8 +939,8 @@ pgf_lzr_linearize_tree(PgfLzr* lzr, PgfCncTree ctree, size_t lin_idx)
if ((*lzr->funcs)->begin_phrase && fapp->ccat != NULL) {
(*lzr->funcs)->begin_phrase(lzr->funcs,
fun->absfun->type->cid,
fapp->fid, lin_idx,
fapp->ccat->cnccat->abscat->name,
fapp->fid, fapp->ccat->cnccat->labels[lin_idx],
fun->absfun->name);
}
@@ -949,8 +949,8 @@ pgf_lzr_linearize_tree(PgfLzr* lzr, PgfCncTree ctree, size_t lin_idx)
if ((*lzr->funcs)->end_phrase && fapp->ccat != NULL) {
(*lzr->funcs)->end_phrase(lzr->funcs,
fun->absfun->type->cid,
fapp->fid, lin_idx,
fapp->ccat->cnccat->abscat->name,
fapp->fid, fapp->ccat->cnccat->labels[lin_idx],
fun->absfun->name);
}
break;
@@ -979,7 +979,7 @@ pgf_lzr_linearize_tree(PgfLzr* lzr, PgfCncTree ctree, size_t lin_idx)
if ((*lzr->funcs)->begin_phrase) {
(*lzr->funcs)->begin_phrase(lzr->funcs,
cat, flit->fid, 0,
cat, flit->fid, "s",
"");
}
@@ -1011,7 +1011,7 @@ pgf_lzr_linearize_tree(PgfLzr* lzr, PgfCncTree ctree, size_t lin_idx)
if ((*lzr->funcs)->end_phrase) {
(*lzr->funcs)->end_phrase(lzr->funcs,
cat, flit->fid, 0,
cat, flit->fid, "s",
"");
}
+2 -2
View File
@@ -83,10 +83,10 @@ struct PgfLinFuncs
void (*symbol_token)(PgfLinFuncs** self, PgfToken tok);
/// Begin phrase
void (*begin_phrase)(PgfLinFuncs** self, PgfCId cat, int fid, size_t lindex, PgfCId fun);
void (*begin_phrase)(PgfLinFuncs** self, PgfCId cat, int fid, GuString ann, PgfCId fun);
/// End phrase
void (*end_phrase)(PgfLinFuncs** self, PgfCId cat, int fid, size_t lindex, PgfCId fun);
void (*end_phrase)(PgfLinFuncs** self, PgfCId cat, int fid, GuString ann, PgfCId fun);
/// handling nonExist
void (*symbol_ne)(PgfLinFuncs** self);
+13 -10
View File
@@ -6,11 +6,12 @@
static PgfExprProb*
pgf_match_string_lit(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool)
{
gu_assert(lin_idx == 0);
if (strcmp(ann,"s") != 0)
return NULL;
const uint8_t* buf = (uint8_t*) (sentence + *poffset);
const uint8_t* p = buf;
@@ -51,7 +52,7 @@ pgf_predict_empty_next(GuEnum* self, void* to, GuPool* pool)
static GuEnum*
pgf_predict_empty(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString prefix,
GuPool *out_pool)
{
@@ -67,11 +68,12 @@ static PgfLiteralCallback pgf_string_literal_callback =
static PgfExprProb*
pgf_match_int_lit(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool)
{
gu_assert(lin_idx == 0);
if (strcmp(ann,"s") != 0)
return NULL;
const uint8_t* buf = (uint8_t*) (sentence + *poffset);
const uint8_t* p = buf;
@@ -121,11 +123,12 @@ static PgfLiteralCallback pgf_int_literal_callback =
static PgfExprProb*
pgf_match_float_lit(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool)
{
gu_assert(lin_idx == 0);
if (strcmp(ann,"s") != 0)
return NULL;
const uint8_t* buf = (uint8_t*) (sentence + *poffset);
const uint8_t* p = buf;
@@ -226,11 +229,11 @@ pgf_match_name_morpho_callback(PgfMorphoCallback* self_,
static PgfExprProb*
pgf_match_name_lit(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool)
{
if (lin_idx != 0)
if (strcmp(ann,"s") != 0)
return NULL;
GuPool* tmp_pool = gu_local_pool();
@@ -349,7 +352,7 @@ pgf_match_unknown_morpho_callback(PgfMorphoCallback* self_,
static PgfExprProb*
pgf_match_unknown_lit(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool)
{
+2 -2
View File
@@ -869,7 +869,7 @@ pgf_lookup_symbol_token(PgfLinFuncs** self, PgfToken token)
}
static void
pgf_lookup_begin_phrase(PgfLinFuncs** self, PgfCId cat, int fid, size_t lindex, PgfCId funname)
pgf_lookup_begin_phrase(PgfLinFuncs** self, PgfCId cat, int fid, GuString ann, PgfCId funname)
{
PgfLookupState* st = gu_container(self, PgfLookupState, funcs);
@@ -883,7 +883,7 @@ pgf_lookup_begin_phrase(PgfLinFuncs** self, PgfCId cat, int fid, size_t lindex,
}
static void
pgf_lookup_end_phrase(PgfLinFuncs** self, PgfCId cat, int fid, size_t lindex, PgfCId fun)
pgf_lookup_end_phrase(PgfLinFuncs** self, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfLookupState* st = gu_container(self, PgfLookupState, funcs);
st->curr_absfun = NULL;
+256 -346
View File
@@ -61,6 +61,14 @@ typedef struct {
typedef enum { BIND_NONE, BIND_HARD, BIND_SOFT } BIND_TYPE;
typedef struct {
PgfProductionIdx* idx;
size_t offset;
size_t sym_idx;
} PgfLexiconIdxEntry;
typedef GuBuf PgfLexiconIdx;
struct PgfParseState {
PgfParseState* next;
@@ -74,6 +82,8 @@ struct PgfParseState {
size_t end_offset;
prob_t viterbi_prob;
PgfLexiconIdx* lexicon_idx;
};
typedef struct PgfAnswers {
@@ -113,43 +123,10 @@ struct PgfItem {
prob_t inside_prob;
};
static PgfSymbol
pgf_prev_extern_sym(PgfSymbol sym)
{
GuVariantInfo i = gu_variant_open(sym);
switch (i.tag) {
case PGF_SYMBOL_CAT:
return *((PgfSymbol*) (((PgfSymbolCat*) i.data)+1));
case PGF_SYMBOL_KP:
return *((PgfSymbol*) (((PgfSymbolKP*) i.data)+1));
case PGF_SYMBOL_KS: {
PgfSymbolKS* sks = (PgfSymbolKS*) i.data;
size_t tok_len = strlen(sks->token);
return *((PgfSymbol*) (((uint8_t*) sks)+sizeof(PgfSymbolKS)+tok_len+1));
}
case PGF_SYMBOL_LIT:
return *((PgfSymbol*) (((PgfSymbolLit*) i.data)+1));
case PGF_SYMBOL_VAR:
return *((PgfSymbol*) (((PgfSymbolVar*) i.data)+1));
case PGF_SYMBOL_BIND:
case PGF_SYMBOL_SOFT_BIND:
case PGF_SYMBOL_SOFT_SPACE:
return *((PgfSymbol*) (((PgfSymbolBIND*) i.data)+1));
case PGF_SYMBOL_CAPIT:
case PGF_SYMBOL_ALL_CAPIT:
return *((PgfSymbol*) (((PgfSymbolCAPIT*) i.data)+1));
case PGF_SYMBOL_NE:
return *((PgfSymbol*) (((PgfSymbolNE*) i.data)+1));
default:
gu_impossible();
return gu_null_variant;
}
}
static PgfSymbol
static PgfSymbols*
pgf_collect_extern_tok(PgfParsing* ps, size_t start_offset, size_t end_offset)
{
PgfSymbol sym = gu_null_variant;
GuBuf* syms = gu_new_buf(PgfSymbol, ps->pool);
const uint8_t* start = (uint8_t*) ps->sentence+start_offset;
const uint8_t* end = (uint8_t*) ps->sentence+end_offset;
@@ -163,16 +140,15 @@ pgf_collect_extern_tok(PgfParsing* ps, size_t start_offset, size_t end_offset)
ucs = gu_utf8_decode(&p);
}
PgfSymbol new_sym;
PgfSymbol sym;
PgfSymbolKS* sks = (PgfSymbolKS*)
gu_alloc_variant(PGF_SYMBOL_KS,
sizeof(PgfSymbol)+sizeof(PgfSymbolKS)+len+1,
gu_alignof(PgfSymbolKS),
&new_sym, ps->pool);
sizeof(PgfSymbolKS)+len+1,
gu_alignof(PgfSymbolKS),
&sym, ps->pool);
memcpy((char*) sks->token, start, len);
((char*) sks->token)[len] = 0;
*((PgfSymbol*) (((uint8_t*) sks)+sizeof(PgfSymbolKS)+len+1)) = sym;
sym = new_sym;
gu_buf_push(syms, PgfSymbol, sym);
start = p;
while (gu_ucs_is_space(ucs)) {
@@ -181,68 +157,16 @@ pgf_collect_extern_tok(PgfParsing* ps, size_t start_offset, size_t end_offset)
}
}
return sym;
}
static size_t
pgf_item_symbols_length(PgfItem* item)
{
GuVariantInfo i = gu_variant_open(item->prod);
switch (i.tag) {
case PGF_PRODUCTION_APPLY: {
PgfProductionApply* papp = i.data;
return gu_seq_length(papp->fun->lins[item->conts->lin_idx]->syms);
}
case PGF_PRODUCTION_COERCE: {
return 1;
}
case PGF_PRODUCTION_EXTERN: {
PgfProductionExtern* pext = i.data;
PgfSymbols* syms;
if (pext->lins != NULL &&
(syms = gu_seq_get(pext->lins,PgfSymbols*,item->conts->lin_idx)) != NULL) {
return gu_seq_length(syms);
} else {
int seq_len = 0;
PgfSymbol sym = item->curr_sym;
while (!gu_variant_is_null(sym)) {
seq_len++;
sym = pgf_prev_extern_sym(sym);
}
return seq_len;
}
}
default:
gu_impossible();
return 0;
}
}
static PgfSymbols*
pgf_extern_syms_get(PgfItem* item, GuPool* pool)
{
int syms_len = pgf_item_symbols_length(item);
PgfSymbols* syms =
gu_new_seq(PgfSymbol, syms_len, pool);
PgfSymbol sym = item->curr_sym;
while (!gu_variant_is_null(sym)) {
gu_seq_set(syms, PgfSymbol, --syms_len, sym);
sym = pgf_prev_extern_sym(sym);
}
return syms;
return gu_buf_data_seq(syms);
}
#ifdef PGF_PARSER_DEBUG
PGF_INTERNAL void
pgf_print_fid(int fid, GuOut* out, GuExn* err);
PGF_INTERNAL_DECL void
pgf_print_symbol(PgfSymbol sym, GuOut *out, GuExn *err);
#ifdef PGF_PARSER_DEBUG
static void
pgf_item_symbols(PgfItem* item,
size_t* lin_idx, PgfSymbols** syms,
@@ -267,11 +191,7 @@ pgf_item_symbols(PgfItem* item,
}
case PGF_PRODUCTION_EXTERN: {
PgfProductionExtern* pext = i.data;
if (pext->lins == NULL ||
(*syms = gu_seq_get(pext->lins, PgfSymbols*, item->conts->lin_idx)) == NULL) {
*syms = pgf_extern_syms_get(item, pool);
}
*syms = pext->lins[item->conts->lin_idx];
break;
}
default:
@@ -603,16 +523,11 @@ pgf_item_set_curr_symbol(PgfItem* item, GuPool* pool)
case PGF_PRODUCTION_EXTERN: {
PgfProductionExtern* pext = i.data;
PgfSymbols* syms;
if (pext->lins != NULL &&
(syms = gu_seq_get(pext->lins,PgfSymbols*,item->conts->lin_idx)) != NULL) {
if (item->sym_idx == gu_seq_length(syms)) {
item->curr_sym = gu_null_variant;
} else {
item->curr_sym = gu_seq_get(syms, PgfSymbol, item->sym_idx);
}
} else {
PgfSymbols* syms = pext->lins[item->conts->lin_idx];
if (item->sym_idx == gu_seq_length(syms)) {
item->curr_sym = gu_null_variant;
} else {
item->curr_sym = gu_seq_get(syms, PgfSymbol, item->sym_idx);
}
break;
}
@@ -781,16 +696,6 @@ pgf_result_production(PgfParsing* ps,
static void
pgf_parsing_complete(PgfParsing* ps, PgfItem* item, PgfExprProb *ep);
static void
pgf_parsing_push_item(PgfParseState* state, PgfItem* item)
{
if (gu_buf_length(state->agenda) == 0) {
state->viterbi_prob =
item->inside_prob+item->conts->outside_prob;
}
gu_buf_heap_push(state->agenda, pgf_item_prob_order, &item);
}
static void
pgf_parsing_push_production(PgfParsing* ps, PgfParseState* state,
PgfItemConts* conts, PgfProduction prod)
@@ -822,7 +727,7 @@ pgf_parsing_combine(PgfParsing* ps,
}
pgf_item_advance(item, ps->pool);
pgf_parsing_push_item(before, item);
gu_buf_heap_push(before->agenda, pgf_item_prob_order, &item);
}
static PgfProduction
@@ -851,36 +756,7 @@ pgf_parsing_new_production(PgfItem* item, PgfExprProb *ep, GuPool *pool)
break;
}
case PGF_PRODUCTION_EXTERN: {
PgfProductionExtern* pext = i.data;
if (pext->lins == NULL ||
gu_seq_get(pext->lins,PgfSymbols*,item->conts->lin_idx) == NULL) {
PgfSymbols* syms =
pgf_extern_syms_get(item, pool);
size_t n_lins = item->conts->ccat->cnccat->n_lins;
PgfProductionExtern* new_pext = (PgfProductionExtern*)
gu_new_variant(PGF_PRODUCTION_EXTERN,
PgfProductionExtern,
&prod, pool);
new_pext->ep = ep;
new_pext->lins = gu_new_seq(PgfSymbols*, n_lins, pool);
if (pext->lins == NULL) {
for (size_t i = 0; i < n_lins; i++) {
gu_seq_set(new_pext->lins,PgfSymbols*,i,NULL);
}
} else {
for (size_t i = 0; i < n_lins; i++) {
gu_seq_set(new_pext->lins,PgfSymbols*,i,
gu_seq_get(pext->lins,PgfSymbols*,i));
}
}
gu_seq_set(new_pext->lins,PgfSymbols*,item->conts->lin_idx,syms);
} else {
prod = item->prod;
}
prod = item->prod;
break;
}
default:
@@ -1022,9 +898,65 @@ pgf_parsing_complete(PgfParsing* ps, PgfItem* item, PgfExprProb *ep)
}
}
PGF_INTERNAL_DECL int
pgf_symbols_cmp(PgfCohortSpot* spot,
PgfSymbols* syms, size_t* sym_idx,
bool case_sensitive);
static void
pgf_parsing_lookahead(PgfParsing *ps, PgfParseState* state,
int i, int j, ptrdiff_t min, ptrdiff_t max)
{
// This is a variation of a binary search algorithm which
// can retrieve all prefixes of a string with minimal
// comparisons, i.e. there is no need to lookup every
// prefix separately.
while (i <= j) {
int k = (i+j) / 2;
PgfSequence* seq = gu_seq_index(ps->concr->sequences, PgfSequence, k);
PgfCohortSpot start = {0, ps->sentence + state->end_offset};
PgfCohortSpot current = start;
size_t sym_idx = 0;
int cmp = pgf_symbols_cmp(&current, seq->syms, &sym_idx, ps->case_sensitive);
if (cmp < 0) {
j = k-1;
} else if (cmp > 0) {
ptrdiff_t len = current.ptr - start.ptr;
if (min <= len)
pgf_parsing_lookahead(ps, state, i, k-1, min, len);
if (len+1 <= max)
pgf_parsing_lookahead(ps, state, k+1, j, len+1, max);
break;
} else {
ptrdiff_t len = current.ptr - start.ptr;
if (min <= len-1)
pgf_parsing_lookahead(ps, state, i, k-1, min, len-1);
if (seq->idx != NULL) {
PgfLexiconIdxEntry* entry = gu_buf_extend(state->lexicon_idx);
entry->idx = seq->idx;
entry->offset = (size_t) (current.ptr - ps->sentence);
entry->sym_idx = sym_idx;
}
if (len+1 <= max)
pgf_parsing_lookahead(ps, state, k+1, j, len+1, max);
break;
}
}
}
static PgfParseState*
pgf_new_parse_state(PgfParsing* ps, size_t start_offset,
BIND_TYPE bind_type)
BIND_TYPE bind_type,
prob_t viterbi_prob)
{
PgfParseState** pstate;
if (ps->before == NULL && start_offset == 0)
@@ -1077,172 +1009,36 @@ pgf_new_parse_state(PgfParsing* ps, size_t start_offset,
(start_offset == end_offset);
state->start_offset = start_offset;
state->end_offset = end_offset;
state->viterbi_prob = 0;
state->viterbi_prob = viterbi_prob;
state->lexicon_idx =
gu_new_buf(PgfLexiconIdxEntry, ps->pool);
if (ps->before == NULL && start_offset == 0)
state->needs_bind = false;
if (gu_seq_length(ps->concr->sequences) > 0) {
// Add epsilon lexical rules to the bottom up index
PgfSequence* seq = gu_seq_index(ps->concr->sequences, PgfSequence, 0);
if (gu_seq_length(seq->syms) == 0 && seq->idx != NULL) {
PgfLexiconIdxEntry* entry = gu_buf_extend(state->lexicon_idx);
entry->idx = seq->idx;
entry->offset = state->start_offset;
entry->sym_idx= 0;
}
// Add non-epsilon lexical rules to the bottom up index
if (!state->needs_bind) {
pgf_parsing_lookahead(ps, state,
0, gu_seq_length(ps->concr->sequences)-1,
1, strlen(ps->sentence)-state->end_offset);
}
}
*pstate = state;
return state;
}
PGF_INTERNAL_DECL int
pgf_symbols_cmp(PgfCohortSpot* spot,
PgfSymbols* syms, size_t* sym_idx,
bool case_sensitive);
static bool
pgf_parsing_scan_helper(PgfParsing *ps, PgfParseState* state,
int i, int j, ptrdiff_t min, ptrdiff_t max)
{
// This is a variation of a binary search algorithm which
// can retrieve all prefixes of a string with minimal
// comparisons, i.e. there is no need to lookup every
// prefix separately.
bool found = false;
while (i <= j) {
int k = (i+j) / 2;
PgfSequence* seq = gu_seq_index(ps->concr->sequences, PgfSequence, k);
PgfCohortSpot start = {0, ps->sentence+state->end_offset};
PgfCohortSpot current = start;
size_t sym_idx = 0;
int cmp = pgf_symbols_cmp(&current, seq->syms, &sym_idx, ps->case_sensitive);
if (cmp < 0) {
j = k-1;
} else if (cmp > 0) {
ptrdiff_t len = current.ptr - start.ptr;
if (min <= len)
if (pgf_parsing_scan_helper(ps, state, i, k-1, min, len))
found = true;
if (len+1 <= max)
if (pgf_parsing_scan_helper(ps, state, k+1, j, len+1, max))
found = true;
break;
} else {
ptrdiff_t len = current.ptr - start.ptr;
if (min <= len)
if (pgf_parsing_scan_helper(ps, state, i, k-1, min, len))
found = true;
// Here we do bottom-up prediction for all lexical categories.
// The epsilon productions will be predicted in top-down
// fashion while parsing.
if (seq->idx != NULL && len > 0) {
found = true;
// A new state will mark the end of the current match
PgfParseState* new_state =
pgf_new_parse_state(ps, (size_t) (current.ptr - ps->sentence), BIND_NONE);
// Bottom-up prediction for lexical rules
size_t n_entries = gu_buf_length(seq->idx);
for (size_t i = 0; i < n_entries; i++) {
PgfProductionIdxEntry* entry =
gu_buf_index(seq->idx, PgfProductionIdxEntry, i);
PgfItemConts* conts =
pgf_parsing_get_conts(state,
entry->ccat, entry->lin_idx,
ps->pool);
// Create the new category if it doesn't exist yet
PgfCCat* tmp_ccat = pgf_parsing_get_completed(new_state, conts);
PgfCCat* ccat = tmp_ccat;
if (ccat == NULL) {
ccat = pgf_parsing_create_completed(ps, new_state, conts, INFINITY);
}
// Add the production
if (ccat->prods == NULL || ccat->n_synprods >= gu_seq_length(ccat->prods)) {
ccat->prods = gu_realloc_seq(ccat->prods, PgfProduction, ccat->n_synprods+1);
}
GuVariantInfo i;
i.tag = PGF_PRODUCTION_APPLY;
i.data = entry->papp;
PgfProduction prod = gu_variant_close(i);
gu_seq_set(ccat->prods, PgfProduction, ccat->n_synprods++, prod);
// Update the category's probability to be minimum
if (ccat->viterbi_prob > entry->papp->fun->ep->prob)
ccat->viterbi_prob = entry->papp->fun->ep->prob;
#ifdef PGF_PARSER_DEBUG
GuPool* tmp_pool = gu_new_pool();
GuOut* out = gu_file_out(stderr, tmp_pool);
GuExn* err = gu_exn(tmp_pool);
if (tmp_ccat == NULL) {
gu_printf(out, err, "[");
pgf_print_range(state, new_state, out, err);
gu_puts("; ", out, err);
pgf_print_fid(conts->ccat->fid, out, err);
gu_printf(out, err, "; %d; ",
conts->lin_idx);
pgf_print_fid(ccat->fid, out, err);
gu_puts("] ", out, err);
pgf_print_fid(ccat->fid, out, err);
gu_printf(out, err, ".chunk_count=%d\n", ccat->chunk_count);
}
pgf_print_production(ccat->fid, prod, out, err);
gu_pool_free(tmp_pool);
#endif
}
}
if (len <= max)
if (pgf_parsing_scan_helper(ps, state, k+1, j, len, max))
found = true;
break;
}
}
return found;
}
static void
pgf_parsing_scan(PgfParsing *ps)
{
size_t len = strlen(ps->sentence);
PgfParseState* state =
pgf_new_parse_state(ps, 0, BIND_SOFT);
while (state != NULL && state->end_offset < len) {
if (state->needs_bind) {
// We have encountered two tokens without space in between.
// Those can be accepted only if there is a BIND token
// in between. We encode this by having one more state
// at the same offset. A transition between these two
// states is possible only with the BIND token.
state =
pgf_new_parse_state(ps, state->end_offset, BIND_HARD);
}
if (!pgf_parsing_scan_helper
(ps, state,
0, gu_seq_length(ps->concr->sequences)-1,
1, len-state->end_offset)) {
// skip one character and try again
GuString s = ps->sentence+state->end_offset;
gu_utf8_decode((const uint8_t**) &s);
pgf_new_parse_state(ps, s-ps->sentence, BIND_NONE);
}
if (state == ps->before)
state = ps->after;
else
state = state->next;
}
}
static void
pgf_parsing_add_transition(PgfParsing* ps, PgfToken tok, PgfItem* item)
{
@@ -1262,8 +1058,9 @@ pgf_parsing_add_transition(PgfParsing* ps, PgfToken tok, PgfItem* item)
if (!ps->before->needs_bind && cmp_string(&current, tok, ps->case_sensitive) == 0) {
PgfParseState* state =
pgf_new_parse_state(ps, (current.ptr - ps->sentence),
BIND_NONE);
pgf_parsing_push_item(state, item);
BIND_NONE,
item->inside_prob+item->conts->outside_prob);
gu_buf_heap_push(state->agenda, pgf_item_prob_order, &item);
} else {
pgf_item_free(ps, item);
}
@@ -1273,17 +1070,18 @@ pgf_parsing_add_transition(PgfParsing* ps, PgfToken tok, PgfItem* item)
static void
pgf_parsing_predict_lexeme(PgfParsing* ps, PgfItemConts* conts,
PgfProductionIdxEntry* entry,
size_t offset)
size_t offset, size_t sym_idx)
{
GuVariantInfo i = { PGF_PRODUCTION_APPLY, entry->papp };
PgfProduction prod = gu_variant_close(i);
PgfItem* item =
pgf_new_item(ps, conts, prod);
PgfSymbols* syms = entry->papp->fun->lins[conts->lin_idx]->syms;
item->sym_idx = gu_seq_length(syms);
item->sym_idx = sym_idx;
pgf_item_set_curr_symbol(item, ps->pool);
prob_t prob = item->inside_prob+item->conts->outside_prob;
PgfParseState* state =
pgf_new_parse_state(ps, offset, BIND_NONE);
pgf_new_parse_state(ps, offset, BIND_NONE, prob);
if (state->viterbi_prob > prob) {
state->viterbi_prob = prob;
}
@@ -1337,36 +1135,34 @@ pgf_parsing_td_predict(PgfParsing* ps,
pgf_parsing_push_production(ps, ps->before, conts, prod);
}
// Top-down prediction for epsilon lexical rules if any
PgfSequence* seq = gu_seq_index(ps->concr->sequences, PgfSequence, 0);
if (gu_seq_length(seq->syms) == 0 && seq->idx != NULL) {
// Bottom-up prediction for lexical and epsilon rules
size_t n_idcs = gu_buf_length(ps->before->lexicon_idx);
for (size_t i = 0; i < n_idcs; i++) {
PgfLexiconIdxEntry* lentry =
gu_buf_index(ps->before->lexicon_idx, PgfLexiconIdxEntry, i);
PgfProductionIdxEntry key;
key.ccat = ccat;
key.lin_idx = lin_idx;
key.papp = NULL;
PgfProductionIdxEntry* value =
gu_seq_binsearch(gu_buf_data_seq(seq->idx),
gu_seq_binsearch(gu_buf_data_seq(lentry->idx),
pgf_production_idx_entry_order,
PgfProductionIdxEntry, &key);
if (value != NULL) {
GuVariantInfo i = { PGF_PRODUCTION_APPLY, value->papp };
PgfProduction prod = gu_variant_close(i);
pgf_parsing_push_production(ps, ps->before, conts, prod);
pgf_parsing_predict_lexeme(ps, conts, value, lentry->offset, lentry->sym_idx);
PgfProductionIdxEntry* start =
gu_buf_data(seq->idx);
gu_buf_data(lentry->idx);
PgfProductionIdxEntry* end =
start + gu_buf_length(seq->idx)-1;
start + gu_buf_length(lentry->idx)-1;
PgfProductionIdxEntry* left = value-1;
while (left >= start &&
value->ccat->fid == left->ccat->fid &&
value->lin_idx == left->lin_idx) {
GuVariantInfo i = { PGF_PRODUCTION_APPLY, left->papp };
PgfProduction prod = gu_variant_close(i);
pgf_parsing_push_production(ps, ps->before, conts, prod);
pgf_parsing_predict_lexeme(ps, conts, left, lentry->offset, lentry->sym_idx);
left--;
}
@@ -1374,9 +1170,7 @@ pgf_parsing_td_predict(PgfParsing* ps,
while (right <= end &&
value->ccat->fid == right->ccat->fid &&
value->lin_idx == right->lin_idx) {
GuVariantInfo i = { PGF_PRODUCTION_APPLY, right->papp };
PgfProduction prod = gu_variant_close(i);
pgf_parsing_push_production(ps, ps->before, conts, prod);
pgf_parsing_predict_lexeme(ps, conts, right, lentry->offset, lentry->sym_idx);
right++;
}
}
@@ -1415,7 +1209,7 @@ pgf_parsing_pre(PgfParsing* ps, PgfItem* item, PgfSymbols* syms)
} else {
item->alt = 0;
pgf_item_advance(item, ps->pool);
pgf_parsing_push_item(ps->before, item);
gu_buf_heap_push(ps->before->agenda, pgf_item_prob_order, &item);
}
}
@@ -1514,28 +1308,40 @@ pgf_parsing_symbol(PgfParsing* ps, PgfItem* item, PgfSymbol sym)
if (callback != NULL) {
ep = callback->match(callback, ps->concr,
slit->r,
parg->ccat->cnccat->labels[slit->r],
ps->sentence, &offset,
ps->out_pool);
}
}
if (ep != NULL) {
PgfSymbols* syms =
pgf_collect_extern_tok(ps, start, offset);
size_t n_lins = conts->ccat->cnccat->n_lins;
PgfProduction prod;
PgfProductionExtern* pext =
gu_new_variant(PGF_PRODUCTION_EXTERN,
PgfProductionExtern,
&prod, ps->pool);
pext->ep = ep;
pext->lins = NULL;
gu_new_flex_variant(PGF_PRODUCTION_EXTERN,
PgfProductionExtern,
lins, n_lins,
&prod, ps->pool);
pext->ep = ep;
pext->n_lins = n_lins;
for (size_t i = 0; i < n_lins; i++) {
pext->lins[i] = NULL;
}
pext->lins[conts->lin_idx] = syms;
PgfItem* item =
pgf_new_item(ps, conts, prod);
item->curr_sym = pgf_collect_extern_tok(ps,start,offset);
item->sym_idx = pgf_item_symbols_length(item);
item->curr_sym = gu_null_variant;
item->sym_idx = gu_seq_length(syms);
PgfParseState* state =
pgf_new_parse_state(ps, offset, BIND_NONE);
pgf_parsing_push_item(state, item);
pgf_new_parse_state(ps, offset, BIND_NONE,
item->inside_prob+item->conts->outside_prob);
gu_buf_heap_push(state->agenda, pgf_item_prob_order, &item);
match = true;
}
}
@@ -1578,10 +1384,11 @@ pgf_parsing_symbol(PgfParsing* ps, PgfItem* item, PgfSymbol sym)
if (ps->before->start_offset == ps->before->end_offset &&
ps->before->needs_bind) {
PgfParseState* state =
pgf_new_parse_state(ps, ps->before->end_offset, BIND_HARD);
pgf_new_parse_state(ps, ps->before->end_offset, BIND_HARD,
item->inside_prob+item->conts->outside_prob);
if (state != NULL) {
pgf_item_advance(item, ps->pool);
pgf_parsing_push_item(state, item);
gu_buf_heap_push(state->agenda, pgf_item_prob_order, &item);
} else {
pgf_item_free(ps, item);
}
@@ -1595,10 +1402,11 @@ pgf_parsing_symbol(PgfParsing* ps, PgfItem* item, PgfSymbol sym)
if (ps->before->start_offset == ps->before->end_offset) {
if (ps->before->needs_bind) {
PgfParseState* state =
pgf_new_parse_state(ps, ps->before->end_offset, BIND_HARD);
pgf_new_parse_state(ps, ps->before->end_offset, BIND_HARD,
item->inside_prob+item->conts->outside_prob);
if (state != NULL) {
pgf_item_advance(item, ps->pool);
pgf_parsing_push_item(state, item);
gu_buf_heap_push(state->agenda, pgf_item_prob_order, &item);
} else {
pgf_item_free(ps, item);
}
@@ -1607,12 +1415,13 @@ pgf_parsing_symbol(PgfParsing* ps, PgfItem* item, PgfSymbol sym)
}
} else {
pgf_item_advance(item, ps->pool);
pgf_parsing_push_item(ps->before, item);
gu_buf_heap_push(ps->before->agenda, pgf_item_prob_order, &item);
}
break;
}
case PGF_SYMBOL_CAPIT:
case PGF_SYMBOL_ALL_CAPIT: {
printf("PGF_SYMBOL_CAPIT\n");
pgf_item_advance(item, ps->pool);
pgf_parsing_symbol(ps, item, item->curr_sym);
break;
@@ -1857,7 +1666,8 @@ pgf_parsing_init(PgfConcr* concr, PgfCId cat,
ps->heuristic_factor = heuristic_factor;
}
pgf_parsing_scan(ps);
PgfParseState* state =
pgf_new_parse_state(ps, 0, BIND_SOFT, 0);
int fidString = -1;
PgfCCat* start_ccat = gu_new(PgfCCat, ps->pool);
@@ -1879,7 +1689,7 @@ pgf_parsing_init(PgfConcr* concr, PgfCId cat,
#endif
PgfItemConts* conts =
pgf_parsing_get_conts(ps->before, start_ccat, 0, ps->pool);
pgf_parsing_get_conts(state, start_ccat, 0, ps->pool);
gu_buf_push(conts->items, PgfItem*, NULL);
size_t n_ccats = gu_seq_length(cnccat->cats);
@@ -2218,6 +2028,8 @@ pgf_process_generated_cat(PgfParsing* ps,
children[i] = pcoerce->coerce;
break;
}
case PGF_PRODUCTION_EXTERN:
just_coercions = false;
}
}
@@ -2363,6 +2175,104 @@ pgf_parse_with_heuristics(PgfConcr* concr, PgfType* typ, GuString sentence,
return &ps->en;
}
PGF_API PgfParsing*
pgf_parse_to_chart(PgfConcr* concr, PgfType* typ, GuString sentence,
double heuristics,
PgfCallbacksMap* callbacks,
size_t n_roots,
GuExn* err,
GuPool* pool, GuPool* out_pool)
{
if (concr->sequences == NULL ||
concr->cnccats == NULL) {
GuExnData* err_data = gu_raise(err, PgfExn);
if (err_data) {
err_data->data = "The concrete syntax is not loaded";
return NULL;
}
}
// Begin parsing a sentence with the specified category
PgfParsing* ps =
pgf_parsing_init(concr, typ->cid, sentence, heuristics, callbacks, NULL, err, pool, out_pool);
if (ps == NULL) {
return NULL;
}
#ifdef PGF_COUNTS_DEBUG
pgf_parsing_print_counts(ps);
#endif
while (gu_buf_length(ps->expr_queue) < n_roots) {
if (!pgf_parsing_proceed(ps)) {
break;
}
#ifdef PGF_COUNTS_DEBUG
pgf_parsing_print_counts(ps);
#endif
}
return ps;
}
PGF_API PgfCCats*
pgf_get_parse_roots(PgfParsing* ps, GuPool* pool)
{
size_t n_cats = 0;
size_t n_states = gu_buf_length(ps->expr_queue);
GuSeq* roots = gu_new_seq(PgfCCat*, n_states, pool);
for (size_t i = 0; i < n_states; i++) {
PgfCCat* ccat = gu_buf_get(ps->expr_queue, PgfExprState*, i)->answers->ccat;
bool found = false;
for (size_t j = 0; j < n_cats; j++) {
if (gu_seq_get(roots, PgfCCat*, j) == ccat) {
found = true;
break;
}
}
if (!found) {
gu_seq_set(roots, PgfCCat*, n_cats, ccat);
n_cats++;
}
}
roots->len = n_cats;
return roots;
}
PGF_API GuSeq*
pgf_ccat_to_range(PgfParsing* ps, PgfCCat* ccat, GuPool* pool)
{
PgfParseState* state = ps->before;
GuBuf* buf = gu_new_buf(PgfParseRange, pool);
while (ccat->conts != NULL) {
size_t start = ccat->conts->state->end_offset;
size_t end = start;
while (state != NULL) {
if (pgf_parsing_get_completed(state, ccat->conts) == ccat) {
if (state->start_offset >= start)
end = state->start_offset;
break;
}
state = state->next;
}
if (start != end) {
PgfParseRange* range = gu_buf_extend(buf);
range->start = start;
range->end = end;
range->field = ccat->cnccat->labels[ccat->conts->lin_idx];
}
ccat = ccat->conts->ccat;
}
return gu_buf_data_seq(buf);
}
PGF_API PgfExprEnum*
pgf_parse_with_oracle(PgfConcr* concr, PgfType* typ,
GuString sentence,
+6 -6
View File
@@ -6,7 +6,7 @@
typedef struct {
int start, end;
PgfCId cat;
size_t lin_idx;
GuString ann;
} PgfPhrase;
typedef struct {
@@ -46,14 +46,14 @@ pgf_metrics_lzn_symbol_token(PgfLinFuncs** funcs, PgfToken tok)
}
static void
pgf_metrics_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin_index, PgfCId fun)
pgf_metrics_lzn_begin_phrase(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfMetricsLznState* state = gu_container(funcs, PgfMetricsLznState, funcs);
gu_buf_push(state->marks, int, state->pos);
}
static void
pgf_metrics_lzn_end_phrase1(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin_idx, PgfCId fun)
pgf_metrics_lzn_end_phrase1(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfMetricsLznState* state = gu_container(funcs, PgfMetricsLznState, funcs);
@@ -65,7 +65,7 @@ pgf_metrics_lzn_end_phrase1(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin
phrase->start = start;
phrase->end = end;
phrase->cat = cat;
phrase->lin_idx = lin_idx;
phrase->ann = ann;
gu_buf_push(state->phrases, PgfPhrase*, phrase);
}
}
@@ -85,7 +85,7 @@ pgf_metrics_symbol_bind(PgfLinFuncs** funcs)
}
static void
pgf_metrics_lzn_end_phrase2(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin_idx, PgfCId fun)
pgf_metrics_lzn_end_phrase2(PgfLinFuncs** funcs, PgfCId cat, int fid, GuString ann, PgfCId fun)
{
PgfMetricsLznState* state = gu_container(funcs, PgfMetricsLznState, funcs);
@@ -100,7 +100,7 @@ pgf_metrics_lzn_end_phrase2(PgfLinFuncs** funcs, PgfCId cat, int fid, size_t lin
if (phrase->start == start &&
phrase->end == end &&
strcmp(phrase->cat, cat) == 0 &&
phrase->lin_idx == lin_idx) {
strcmp(phrase->ann, ann) == 0) {
state->matches++;
break;
}
+14
View File
@@ -220,6 +220,20 @@ pgf_category_prob(PgfPGF* pgf, PgfCId catname)
return abscat->prob;
}
PGF_API GuString*
pgf_category_fields(PgfConcr* concr, PgfCId catname, size_t *n_lins)
{
PgfCncCat* cnccat =
gu_map_get(concr->cnccats, catname, PgfCncCat*);
if (!cnccat) {
*n_lins = 0;
return NULL;
}
*n_lins = cnccat->n_lins;
return &cnccat->labels;
}
PGF_API GuString
pgf_language_code(PgfConcr* concr)
{
+13 -4
View File
@@ -90,6 +90,9 @@ pgf_category_context(PgfPGF *gr, PgfCId catname);
PGF_API_DECL prob_t
pgf_category_prob(PgfPGF* pgf, PgfCId catname);
PGF_API GuString*
pgf_category_fields(PgfConcr* concr, PgfCId catname, size_t *n_lins);
PGF_API_DECL void
pgf_iter_functions(PgfPGF* pgf, GuMapItor* itor, GuExn* err);
@@ -163,8 +166,8 @@ pgf_lookup_morpho(PgfConcr *concr, GuString sentence,
PgfMorphoCallback* callback, GuExn* err);
typedef struct {
size_t pos;
GuString ptr;
size_t pos; // position in Unicode characters
GuString ptr; // pointer into the string
} PgfCohortSpot;
typedef struct {
@@ -203,6 +206,12 @@ pgf_parse_with_heuristics(PgfConcr* concr, PgfType* typ,
GuExn* err,
GuPool* pool, GuPool* out_pool);
typedef struct {
size_t start;
size_t end;
GuString field;
} PgfParseRange;
typedef struct PgfOracleCallback PgfOracleCallback;
struct PgfOracleCallback {
@@ -243,11 +252,11 @@ typedef struct PgfLiteralCallback PgfLiteralCallback;
struct PgfLiteralCallback {
PgfExprProb* (*match)(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString sentence, size_t* poffset,
GuPool *out_pool);
GuEnum* (*predict)(PgfLiteralCallback* self, PgfConcr* concr,
size_t lin_idx,
GuString ann,
GuString prefix,
GuPool *out_pool);
};
+106 -39
View File
@@ -114,7 +114,7 @@ pgf_morpho_iter(PgfProductionIdx* idx,
PgfCId lemma = entry->papp->fun->absfun->name;
GuString analysis = entry->ccat->cnccat->labels[entry->lin_idx];
prob_t prob = entry->ccat->cnccat->abscat->prob +
entry->papp->fun->absfun->ep.prob;
callback->callback(callback,
@@ -234,12 +234,13 @@ typedef struct {
GuEnum en;
PgfConcr* concr;
GuString sentence;
GuString current;
size_t len;
PgfMorphoCallback* callback;
GuExn* err;
bool case_sensitive;
GuBuf* spots;
GuBuf* skip_spots;
GuBuf* empty_buf;
GuBuf* found;
} PgfCohortsState;
@@ -255,6 +256,23 @@ cmp_cohort_spot(GuOrder* self, const void* a, const void* b)
static GuOrder
pgf_cohort_spot_order[1] = {{ cmp_cohort_spot }};
static void
pgf_lookup_cohorts_report_skip(PgfCohortsState *state,
PgfCohortSpot* spot)
{
size_t n_spots = gu_buf_length(state->skip_spots);
for (size_t i = 0; i < n_spots; i++) {
PgfCohortSpot* skip_spot =
gu_buf_index(state->skip_spots, PgfCohortSpot, i);
PgfCohortRange* range = gu_buf_insert(state->found, 0);
range->start = *skip_spot;
range->end = *spot;
range->buf = state->empty_buf;
}
gu_buf_flush(state->skip_spots);
}
static void
pgf_lookup_cohorts_helper(PgfCohortsState *state, PgfCohortSpot* spot,
int i, int j, ptrdiff_t min, ptrdiff_t max)
@@ -291,18 +309,23 @@ pgf_lookup_cohorts_helper(PgfCohortsState *state, PgfCohortSpot* spot,
pgf_lookup_cohorts_helper(state, spot, i, k-1, min, len);
if (seq->idx != NULL && gu_buf_length(seq->idx) > 0) {
// Report unknown words
pgf_lookup_cohorts_report_skip(state, spot);
// Report the actual hit
PgfCohortRange* range = gu_buf_insert(state->found, 0);
range->start = *spot;
range->end = current;
range->buf = seq->idx;
}
while (*current.ptr != 0) {
if (!skip_space(&current.ptr, &current.pos))
break;
}
// Schedule the next search spot
while (*current.ptr != 0) {
if (!skip_space(&current.ptr, &current.pos))
break;
}
gu_buf_heap_push(state->spots, pgf_cohort_spot_order, &current);
gu_buf_heap_push(state->spots, pgf_cohort_spot_order, &current);
}
if (len <= max)
pgf_lookup_cohorts_helper(state, spot, k+1, j, len, max);
@@ -318,29 +341,67 @@ pgf_lookup_cohorts_enum_next(GuEnum* self, void* to, GuPool* pool)
PgfCohortsState* state = gu_container(self, PgfCohortsState, en);
while (gu_buf_length(state->found) == 0 &&
gu_buf_length(state->spots) > 0) {
gu_buf_length(state->spots) > 0) {
PgfCohortSpot spot;
gu_buf_heap_pop(state->spots, pgf_cohort_spot_order, &spot);
if (spot.ptr == state->current)
continue;
GuString next_ptr = state->sentence+state->len;
while (gu_buf_length(state->spots) > 0) {
GuString ptr =
gu_buf_index(state->spots, PgfCohortSpot, 0)->ptr;
if (ptr > spot.ptr) {
next_ptr = ptr;
break;
}
gu_buf_heap_pop(state->spots, pgf_cohort_spot_order, &spot);
}
if (*spot.ptr == 0)
break;
bool needs_report = true;
while (next_ptr > spot.ptr) {
pgf_lookup_cohorts_helper
(state, &spot,
0, gu_seq_length(state->concr->sequences)-1,
1, (state->sentence+state->len)-spot.ptr);
pgf_lookup_cohorts_helper
(state, &spot,
0, gu_seq_length(state->concr->sequences)-1,
1, (state->sentence+state->len)-spot.ptr);
if (gu_buf_length(state->found) == 0) {
// skip one character and try again
gu_utf8_decode((const uint8_t**) &spot.ptr);
spot.pos++;
gu_buf_heap_push(state->spots, pgf_cohort_spot_order, &spot);
// got a hit -> exit
if (gu_buf_length(state->found) > 0)
break;
if (needs_report) {
// no hit, but the word must be reported as unknown.
gu_buf_push(state->skip_spots, PgfCohortSpot, spot);
needs_report = false;
}
// skip one character
const uint8_t* ptr = (const uint8_t*) spot.ptr;
GuUCS c = gu_utf8_decode(&ptr);
if (gu_ucs_is_space(c)) {
// We have encounter a space and we must report
// a new unknown word.
pgf_lookup_cohorts_report_skip(state, &spot);
spot.ptr = (GuString) ptr;
spot.pos++;
// Schedule the next search spot
while (*spot.ptr != 0) {
if (!skip_space(&spot.ptr, &spot.pos))
break;
}
gu_buf_heap_push(state->spots, pgf_cohort_spot_order, &spot);
break;
} else {
spot.ptr = (GuString) ptr;
spot.pos++;
}
}
}
PgfCohortSpot end_spot = {state->len, state->sentence+state->len};
pgf_lookup_cohorts_report_skip(state, &end_spot);
PgfCohortRange* pRes = (PgfCohortRange*)to;
if (gu_buf_length(state->found) == 0) {
@@ -349,15 +410,19 @@ pgf_lookup_cohorts_enum_next(GuEnum* self, void* to, GuPool* pool)
pRes->end.pos = 0;
pRes->end.ptr = NULL;
pRes->buf = NULL;
state->current = NULL;
return;
} else do {
} else for (;;) {
*pRes = gu_buf_pop(state->found, PgfCohortRange);
state->current = pRes->start.ptr;
pgf_morpho_iter(pRes->buf, state->callback, state->err);
} while (gu_buf_length(state->found) > 0 &&
gu_buf_index_last(state->found, PgfCohortRange)->end.ptr == pRes->end.ptr);
if (gu_buf_length(state->found) <= 0)
break;
PgfCohortRange* last =
gu_buf_index_last(state->found, PgfCohortRange);
if (last->start.ptr != pRes->start.ptr ||
last->end.ptr != pRes->end.ptr)
break;
}
}
PGF_API GuEnum*
@@ -374,15 +439,17 @@ pgf_lookup_cohorts(PgfConcr *concr, GuString sentence,
}
PgfCohortsState* state = gu_new(PgfCohortsState, pool);
state->en.next = pgf_lookup_cohorts_enum_next;
state->concr = concr;
state->sentence= sentence;
state->len = strlen(sentence);
state->callback= callback;
state->err = err;
state->case_sensitive = pgf_is_case_sensitive(concr);
state->spots = gu_new_buf(PgfCohortSpot, pool);
state->found = gu_new_buf(PgfCohortRange, pool);
state->en.next = pgf_lookup_cohorts_enum_next;
state->concr = concr;
state->sentence = sentence;
state->len = strlen(sentence);
state->callback = callback;
state->err = err;
state->case_sensitive= pgf_is_case_sensitive(concr);
state->spots = gu_new_buf(PgfCohortSpot, pool);
state->skip_spots = gu_new_buf(PgfCohortSpot, pool);
state->empty_buf = gu_new_buf(PgfProductionIdxEntry, pool);
state->found = gu_new_buf(PgfCohortRange, pool);
PgfCohortSpot spot = {0,sentence};
while (*spot.ptr != 0) {
File diff suppressed because it is too large Load Diff
-94
View File
@@ -1,94 +0,0 @@
#ifndef SG_SG_H_
#define SG_SG_H_
typedef long long int SgId;
#include <gu/exn.h>
#include <pgf/pgf.h>
typedef struct SgSG SgSG;
SgSG*
sg_open(const char *filename, GuExn* err);
void
sg_close(SgSG *sg, GuExn* err);
void
sg_begin_trans(SgSG* sg, GuExn* err);
void
sg_commit(SgSG* sg, GuExn* err);
void
sg_rollback(SgSG* sg, GuExn* err);
SgId
sg_insert_expr(SgSG *sg, PgfExpr expr, int wrFlag, GuExn* err);
PgfExpr
sg_get_expr(SgSG *sg, SgId key, GuPool* out_pool, GuExn* err);
typedef struct SgQueryExprResult SgQueryExprResult;
SgQueryExprResult*
sg_query_expr(SgSG *sg, PgfExpr expr, GuPool* pool, GuExn* err);
PgfExpr
sg_query_next(SgSG *sg, SgQueryExprResult* ctxt, SgId* pKey, GuPool* pool, GuExn* err);
void
sg_query_close(SgSG* sg, SgQueryExprResult* ctxt, GuExn* err);
void
sg_update_fts_index(SgSG* sg, PgfPGF* pgf, GuExn* err);
GuSeq*
sg_query_linearization(SgSG *sg, GuString tok, GuPool* pool, GuExn* err);
typedef PgfExpr SgTriple[3];
SgId
sg_insert_triple(SgSG *sg, SgTriple triple, GuExn* err);
int
sg_get_triple(SgSG *sg, SgId key, SgTriple triple,
GuPool* out_pool, GuExn* err);
typedef struct SgTripleResult SgTripleResult;
SgTripleResult*
sg_query_triple(SgSG *sg, SgTriple triple, GuExn* err);
int
sg_triple_result_fetch(SgTripleResult* tres, SgId* pKey, SgTriple triple,
GuPool* out_pool, GuExn* err);
void
sg_triple_result_get_query(SgTripleResult* tres, SgTriple triple);
void
sg_triple_result_close(SgTripleResult* tres, GuExn* err);
typedef struct SgQueryResult SgQueryResult;
SgQueryResult*
sg_query(SgSG *sg, size_t n_triples, SgTriple* triples, GuExn* err);
size_t
sg_query_result_columns(SgQueryResult* qres);
int
sg_query_result_fetch_columns(SgQueryResult* qres, PgfExpr* res,
GuPool* out_pool, GuExn* err);
PgfExpr
sg_query_result_fetch_expr(SgQueryResult* qres, PgfExpr expr,
GuPool* out_pool, GuExn* err);
void
sg_query_result_close(SgQueryResult* qres, GuExn* err);
#endif
File diff suppressed because it is too large Load Diff
-705
View File
@@ -1,705 +0,0 @@
/*
** 2001 September 15
**
** The author disclaims copyright to this source code. In place of
** a legal notice, here is a blessing:
**
** May you do good and not evil.
** May you find forgiveness for yourself and forgive others.
** May you share freely, never taking more than you give.
**
*************************************************************************
** This header file defines the interface that the sqlite B-Tree file
** subsystem. See comments in the source code for a detailed description
** of what each interface routine does.
*/
#ifndef _BTREE_H_
#define _BTREE_H_
/*
** The SQLITE_THREADSAFE macro must be defined as 0, 1, or 2.
** 0 means mutexes are permanently disable and the library is never
** threadsafe. 1 means the library is serialized which is the highest
** level of threadsafety. 2 means the library is multithreaded - multiple
** threads can use SQLite as long as no two threads try to use the same
** database connection at the same time.
**
** Older versions of SQLite used an optional THREADSAFE macro.
** We support that for legacy.
*/
#if !defined(SQLITE_THREADSAFE)
# if defined(THREADSAFE)
# define SQLITE_THREADSAFE THREADSAFE
# else
# define SQLITE_THREADSAFE 1 /* IMP: R-07272-22309 */
# endif
#endif
/*
** CAPI3REF: 64-Bit Integer Types
** KEYWORDS: sqlite_int64 sqlite_uint64
**
** Because there is no cross-platform way to specify 64-bit integer types
** SQLite includes typedefs for 64-bit signed and unsigned integers.
**
** The sqlite3_int64 and sqlite3_uint64 are the preferred type definitions.
** The sqlite_int64 and sqlite_uint64 types are supported for backwards
** compatibility only.
**
** ^The sqlite3_int64 and sqlite_int64 types can store integer values
** between -9223372036854775808 and +9223372036854775807 inclusive. ^The
** sqlite3_uint64 and sqlite_uint64 types can store integer values
** between 0 and +18446744073709551615 inclusive.
*/
#ifdef SQLITE_INT64_TYPE
typedef SQLITE_INT64_TYPE sqlite_int64;
typedef unsigned SQLITE_INT64_TYPE sqlite_uint64;
#elif defined(_MSC_VER) || defined(__BORLANDC__)
typedef __int64 sqlite_int64;
typedef unsigned __int64 sqlite_uint64;
#else
typedef long long int sqlite_int64;
typedef unsigned long long int sqlite_uint64;
#endif
typedef sqlite_int64 sqlite3_int64;
typedef sqlite_uint64 sqlite3_uint64;
/*
** Integers of known sizes. These typedefs might change for architectures
** where the sizes very. Preprocessor macros are available so that the
** types can be conveniently redefined at compile-type. Like this:
**
** cc '-DUINTPTR_TYPE=long long int' ...
*/
#ifndef UINT32_TYPE
# ifdef HAVE_UINT32_T
# define UINT32_TYPE uint32_t
# else
# define UINT32_TYPE unsigned int
# endif
#endif
#ifndef UINT16_TYPE
# ifdef HAVE_UINT16_T
# define UINT16_TYPE uint16_t
# else
# define UINT16_TYPE unsigned short int
# endif
#endif
#ifndef INT16_TYPE
# ifdef HAVE_INT16_T
# define INT16_TYPE int16_t
# else
# define INT16_TYPE short int
# endif
#endif
#ifndef UINT8_TYPE
# ifdef HAVE_UINT8_T
# define UINT8_TYPE uint8_t
# else
# define UINT8_TYPE unsigned char
# endif
#endif
#ifndef INT8_TYPE
# ifdef HAVE_INT8_T
# define INT8_TYPE int8_t
# else
# define INT8_TYPE signed char
# endif
#endif
#ifndef LONGDOUBLE_TYPE
# define LONGDOUBLE_TYPE long double
#endif
typedef sqlite_int64 i64; /* 8-byte signed integer */
typedef sqlite_uint64 u64; /* 8-byte unsigned integer */
typedef UINT32_TYPE u32; /* 4-byte unsigned integer */
typedef UINT16_TYPE u16; /* 2-byte unsigned integer */
typedef INT16_TYPE i16; /* 2-byte signed integer */
typedef UINT8_TYPE u8; /* 1-byte unsigned integer */
typedef INT8_TYPE i8; /* 1-byte signed integer */
/* TODO: This definition is just included so other modules compile. It
** needs to be revisited.
*/
#define SQLITE_N_BTREE_META 16
/*
** If defined as non-zero, auto-vacuum is enabled by default. Otherwise
** it must be turned on for each database using "PRAGMA auto_vacuum = 1".
*/
#ifndef SQLITE_DEFAULT_AUTOVACUUM
#define SQLITE_DEFAULT_AUTOVACUUM 0
#endif
#define BTREE_AUTOVACUUM_NONE 0 /* Do not do auto-vacuum */
#define BTREE_AUTOVACUUM_FULL 1 /* Do full auto-vacuum */
#define BTREE_AUTOVACUUM_INCR 2 /* Incremental vacuum */
/*
** CAPI3REF: Initialize The SQLite Library
**
** ^The sqlite3BtreeInitialize() routine initializes the
** SQLite library. ^The sqlite3BtreeShutdown() routine
** deallocates any resources that were allocated by sqlite3BtreeInitialize().
** These routines are designed to aid in process initialization and
** shutdown on embedded systems. Workstation applications using
** SQLite normally do not need to invoke either of these routines.
**
** A call to sqlite3BtreeInitialize() is an "effective" call if it is
** the first time sqlite3BtreeInitialize() is invoked during the lifetime of
** the process, or if it is the first time sqlite3BtreeInitialize() is invoked
** following a call to sqlite3BtreeShutdown(). ^(Only an effective call
** of sqlite3BtreeInitialize() does any initialization. All other calls
** are harmless no-ops.)^
**
** A call to sqlite3BtreeShutdown() is an "effective" call if it is the first
** call to sqlite3BtreeShutdown() since the last sqlite3BtreeInitialize(). ^(Only
** an effective call to sqlite3BtreeShutdown() does any deinitialization.
** All other valid calls to sqlite3BtreeShutdown() are harmless no-ops.)^
**
** The sqlite3BtreeInitialize() interface is threadsafe, but sqlite3BtreeShutdown()
** is not. The sqlite3BtreeShutdown() interface must only be called from a
** single thread. All open [database connections] must be closed and all
** other SQLite resources must be deallocated prior to invoking
** sqlite3BtreeShutdown().
**
** Among other things, ^sqlite3BtreeInitialize() will invoke
** sqlite3_os_init(). Similarly, ^sqlite3BtreeShutdown()
** will invoke sqlite3_os_end().
**
** ^The sqlite3BtreeInitialize() routine returns [SQLITE_OK] on success.
** ^If for some reason, sqlite3BtreeInitialize() is unable to initialize
** the library (perhaps it is unable to allocate a needed resource such
** as a mutex) it returns an [error code] other than [SQLITE_OK].
**
** ^The sqlite3BtreeInitialize() routine is called internally by many other
** SQLite interfaces so that an application usually does not need to
** invoke sqlite3BtreeInitialize() directly. For example, [sqlite3_open()]
** calls sqlite3BtreeInitialize() so the SQLite library will be automatically
** initialized when [sqlite3_open()] is called if it has not be initialized
** already. ^However, if SQLite is compiled with the [SQLITE_OMIT_AUTOINIT]
** compile-time option, then the automatic calls to sqlite3BtreeInitialize()
** are omitted and the application must call sqlite3BtreeInitialize() directly
** prior to using any other SQLite interface. For maximum portability,
** it is recommended that applications always invoke sqlite3BtreeInitialize()
** directly prior to using any other SQLite interface. Future releases
** of SQLite may require this. In other words, the behavior exhibited
** when SQLite is compiled with [SQLITE_OMIT_AUTOINIT] might become the
** default behavior in some future release of SQLite.
**
** The sqlite3_os_init() routine does operating-system specific
** initialization of the SQLite library. The sqlite3_os_end()
** routine undoes the effect of sqlite3_os_init(). Typical tasks
** performed by these routines include allocation or deallocation
** of static resources, initialization of global variables,
** setting up a default [sqlite3_vfs] module, or setting up
** a default configuration using [sqlite3_config()].
**
** The application should never invoke either sqlite3_os_init()
** or sqlite3_os_end() directly. The application should only invoke
** sqlite3BtreeInitialize() and sqlite3BtreeShutdown(). The sqlite3_os_init()
** interface is called automatically by sqlite3BtreeInitialize() and
** sqlite3_os_end() is called by sqlite3BtreeShutdown(). Appropriate
** implementations for sqlite3_os_init() and sqlite3_os_end()
** are built into SQLite when it is compiled for Unix, Windows, or OS/2.
** When [custom builds | built for other platforms]
** (using the [SQLITE_OS_OTHER=1] compile-time
** option) the application must supply a suitable implementation for
** sqlite3_os_init() and sqlite3_os_end(). An application-supplied
** implementation of sqlite3_os_init() or sqlite3_os_end()
** must return [SQLITE_OK] on success and some other [error code] upon
** failure.
*/
int sqlite3BtreeInitialize(void);
int sqlite3BtreeShutdown(void);
/*
** CAPI3REF: Result Codes
** KEYWORDS: {result code definitions}
**
** Many SQLite functions return an integer result code from the set shown
** here in order to indicate success or failure.
**
** New error codes may be added in future versions of SQLite.
**
** See also: [extended result code definitions]
*/
#define SQLITE_OK 0 /* Successful result */
/* beginning-of-error-codes */
#define SQLITE_ERROR 1 /* SQL error or missing database */
#define SQLITE_INTERNAL 2 /* Internal logic error in SQLite */
#define SQLITE_PERM 3 /* Access permission denied */
#define SQLITE_ABORT 4 /* Callback routine requested an abort */
#define SQLITE_BUSY 5 /* The database file is locked */
#define SQLITE_LOCKED 6 /* A table in the database is locked */
#define SQLITE_NOMEM 7 /* A malloc() failed */
#define SQLITE_READONLY 8 /* Attempt to write a readonly database */
#define SQLITE_INTERRUPT 9 /* Operation terminated by sqlite3_interrupt()*/
#define SQLITE_IOERR 10 /* Some kind of disk I/O error occurred */
#define SQLITE_CORRUPT 11 /* The database disk image is malformed */
#define SQLITE_NOTFOUND 12 /* Unknown opcode in sqlite3_file_control() */
#define SQLITE_FULL 13 /* Insertion failed because database is full */
#define SQLITE_CANTOPEN 14 /* Unable to open the database file */
#define SQLITE_PROTOCOL 15 /* Database lock protocol error */
#define SQLITE_EMPTY 16 /* Database is empty */
#define SQLITE_SCHEMA 17 /* The database schema changed */
#define SQLITE_TOOBIG 18 /* String or BLOB exceeds size limit */
#define SQLITE_CONSTRAINT 19 /* Abort due to constraint violation */
#define SQLITE_MISMATCH 20 /* Data type mismatch */
#define SQLITE_MISUSE 21 /* Library used incorrectly */
#define SQLITE_NOLFS 22 /* Uses OS features not supported on host */
#define SQLITE_AUTH 23 /* Authorization denied */
#define SQLITE_FORMAT 24 /* Auxiliary database format error */
#define SQLITE_RANGE 25 /* 2nd parameter to sqlite3_bind out of range */
#define SQLITE_NOTADB 26 /* File opened that is not a database file */
#define SQLITE_NOTICE 27 /* Notifications from sqlite3_log() */
#define SQLITE_WARNING 28 /* Warnings from sqlite3_log() */
#define SQLITE_ROW 100 /* sqlite3_step() has another row ready */
#define SQLITE_DONE 101 /* sqlite3_step() has finished executing */
/* end-of-error-codes */
/*
** CAPI3REF: Extended Result Codes
** KEYWORDS: {extended result code definitions}
**
** In its default configuration, SQLite API routines return one of 30 integer
** [result codes]. However, experience has shown that many of
** these result codes are too coarse-grained. They do not provide as
** much information about problems as programmers might like. In an effort to
** address this, newer versions of SQLite (version 3.3.8 and later) include
** support for additional result codes that provide more detailed information
** about errors. These [extended result codes] are enabled or disabled
** on a per database connection basis using the
** [sqlite3_extended_result_codes()] API. Or, the extended code for
** the most recent error can be obtained using
** [sqlite3_extended_errcode()].
*/
#define SQLITE_IOERR_READ (SQLITE_IOERR | (1<<8))
#define SQLITE_IOERR_SHORT_READ (SQLITE_IOERR | (2<<8))
#define SQLITE_IOERR_WRITE (SQLITE_IOERR | (3<<8))
#define SQLITE_IOERR_FSYNC (SQLITE_IOERR | (4<<8))
#define SQLITE_IOERR_DIR_FSYNC (SQLITE_IOERR | (5<<8))
#define SQLITE_IOERR_TRUNCATE (SQLITE_IOERR | (6<<8))
#define SQLITE_IOERR_FSTAT (SQLITE_IOERR | (7<<8))
#define SQLITE_IOERR_UNLOCK (SQLITE_IOERR | (8<<8))
#define SQLITE_IOERR_RDLOCK (SQLITE_IOERR | (9<<8))
#define SQLITE_IOERR_DELETE (SQLITE_IOERR | (10<<8))
#define SQLITE_IOERR_BLOCKED (SQLITE_IOERR | (11<<8))
#define SQLITE_IOERR_NOMEM (SQLITE_IOERR | (12<<8))
#define SQLITE_IOERR_ACCESS (SQLITE_IOERR | (13<<8))
#define SQLITE_IOERR_CHECKRESERVEDLOCK (SQLITE_IOERR | (14<<8))
#define SQLITE_IOERR_LOCK (SQLITE_IOERR | (15<<8))
#define SQLITE_IOERR_CLOSE (SQLITE_IOERR | (16<<8))
#define SQLITE_IOERR_DIR_CLOSE (SQLITE_IOERR | (17<<8))
#define SQLITE_IOERR_SHMOPEN (SQLITE_IOERR | (18<<8))
#define SQLITE_IOERR_SHMSIZE (SQLITE_IOERR | (19<<8))
#define SQLITE_IOERR_SHMLOCK (SQLITE_IOERR | (20<<8))
#define SQLITE_IOERR_SHMMAP (SQLITE_IOERR | (21<<8))
#define SQLITE_IOERR_SEEK (SQLITE_IOERR | (22<<8))
#define SQLITE_IOERR_DELETE_NOENT (SQLITE_IOERR | (23<<8))
#define SQLITE_IOERR_MMAP (SQLITE_IOERR | (24<<8))
#define SQLITE_IOERR_GETTEMPPATH (SQLITE_IOERR | (25<<8))
#define SQLITE_IOERR_CONVPATH (SQLITE_IOERR | (26<<8))
#define SQLITE_IOERR_VNODE (SQLITE_IOERR | (27<<8))
#define SQLITE_LOCKED_SHAREDCACHE (SQLITE_LOCKED | (1<<8))
#define SQLITE_BUSY_RECOVERY (SQLITE_BUSY | (1<<8))
#define SQLITE_BUSY_SNAPSHOT (SQLITE_BUSY | (2<<8))
#define SQLITE_CANTOPEN_NOTEMPDIR (SQLITE_CANTOPEN | (1<<8))
#define SQLITE_CANTOPEN_ISDIR (SQLITE_CANTOPEN | (2<<8))
#define SQLITE_CANTOPEN_FULLPATH (SQLITE_CANTOPEN | (3<<8))
#define SQLITE_CANTOPEN_CONVPATH (SQLITE_CANTOPEN | (4<<8))
#define SQLITE_CORRUPT_VTAB (SQLITE_CORRUPT | (1<<8))
#define SQLITE_READONLY_RECOVERY (SQLITE_READONLY | (1<<8))
#define SQLITE_READONLY_CANTLOCK (SQLITE_READONLY | (2<<8))
#define SQLITE_READONLY_ROLLBACK (SQLITE_READONLY | (3<<8))
#define SQLITE_READONLY_DBMOVED (SQLITE_READONLY | (4<<8))
#define SQLITE_ABORT_ROLLBACK (SQLITE_ABORT | (2<<8))
#define SQLITE_CONSTRAINT_CHECK (SQLITE_CONSTRAINT | (1<<8))
#define SQLITE_CONSTRAINT_COMMITHOOK (SQLITE_CONSTRAINT | (2<<8))
#define SQLITE_CONSTRAINT_FOREIGNKEY (SQLITE_CONSTRAINT | (3<<8))
#define SQLITE_CONSTRAINT_FUNCTION (SQLITE_CONSTRAINT | (4<<8))
#define SQLITE_CONSTRAINT_NOTNULL (SQLITE_CONSTRAINT | (5<<8))
#define SQLITE_CONSTRAINT_PRIMARYKEY (SQLITE_CONSTRAINT | (6<<8))
#define SQLITE_CONSTRAINT_TRIGGER (SQLITE_CONSTRAINT | (7<<8))
#define SQLITE_CONSTRAINT_UNIQUE (SQLITE_CONSTRAINT | (8<<8))
#define SQLITE_CONSTRAINT_VTAB (SQLITE_CONSTRAINT | (9<<8))
#define SQLITE_CONSTRAINT_ROWID (SQLITE_CONSTRAINT |(10<<8))
#define SQLITE_NOTICE_RECOVER_WAL (SQLITE_NOTICE | (1<<8))
#define SQLITE_NOTICE_RECOVER_ROLLBACK (SQLITE_NOTICE | (2<<8))
#define SQLITE_WARNING_AUTOINDEX (SQLITE_WARNING | (1<<8))
#define SQLITE_AUTH_USER (SQLITE_AUTH | (1<<8))
/* Reserved: 0x00F00000 */
/*
** Forward declarations of structure
*/
typedef struct Btree Btree;
typedef struct BtCursor BtCursor;
typedef struct BtShared BtShared;
typedef struct Mem Mem;
typedef struct KeyInfo KeyInfo;
typedef struct UnpackedRecord UnpackedRecord;
int sqlite3BtreeOpen(
const char *zVfs, /* VFS to use with this b-tree */
const char *zFilename, /* Name of database file to open */
Btree **ppBtree, /* Return open Btree* here */
int flags, /* Flags */
int vfsFlags /* Flags passed through to VFS open */
);
/* The flags parameter to sqlite3BtreeOpen can be the bitwise or of the
** following values.
**
** NOTE: These values must match the corresponding PAGER_ values in
** pager.h.
*/
#define BTREE_OMIT_JOURNAL 1 /* Do not create or use a rollback journal */
#define BTREE_MEMORY 2 /* This is an in-memory DB */
#define BTREE_SINGLE 4 /* The file contains at most 1 b-tree */
#define BTREE_UNORDERED 8 /* Use of a hash implementation is OK */
/*
** CAPI3REF: Flags For File Open Operations
**
** These bit values are intended for use in the
** 3rd parameter to the [sqlite3_open_v2()] interface and
** in the 4th parameter to the [sqlite3_vfs.xOpen] method.
*/
#define SQLITE_OPEN_READONLY 0x00000001 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_READWRITE 0x00000002 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_CREATE 0x00000004 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_DELETEONCLOSE 0x00000008 /* VFS only */
#define SQLITE_OPEN_EXCLUSIVE 0x00000010 /* VFS only */
#define SQLITE_OPEN_AUTOPROXY 0x00000020 /* VFS only */
#define SQLITE_OPEN_URI 0x00000040 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_MEMORY 0x00000080 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_MAIN_DB 0x00000100 /* VFS only */
#define SQLITE_OPEN_TEMP_DB 0x00000200 /* VFS only */
#define SQLITE_OPEN_TRANSIENT_DB 0x00000400 /* VFS only */
#define SQLITE_OPEN_MAIN_JOURNAL 0x00000800 /* VFS only */
#define SQLITE_OPEN_TEMP_JOURNAL 0x00001000 /* VFS only */
#define SQLITE_OPEN_SUBJOURNAL 0x00002000 /* VFS only */
#define SQLITE_OPEN_MASTER_JOURNAL 0x00004000 /* VFS only */
#define SQLITE_OPEN_NOMUTEX 0x00008000 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_FULLMUTEX 0x00010000 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_SHAREDCACHE 0x00020000 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_PRIVATECACHE 0x00040000 /* Ok for sqlite3_open_v2() */
#define SQLITE_OPEN_WAL 0x00080000 /* VFS only */
int sqlite3BtreeClose(Btree*);
int sqlite3BtreeSetCacheSize(Btree*,int);
#if SQLITE_MAX_MMAP_SIZE>0
int sqlite3BtreeSetMmapLimit(Btree*,sqlite3_int64);
#endif
int sqlite3BtreeSetPagerFlags(Btree*,unsigned);
int sqlite3BtreeSyncDisabled(Btree*);
int sqlite3BtreeSetPageSize(Btree *p, int nPagesize, int nReserve, int eFix);
int sqlite3BtreeGetPageSize(Btree*);
int sqlite3BtreeMaxPageCount(Btree*,int);
u32 sqlite3BtreeLastPage(Btree*);
int sqlite3BtreeSecureDelete(Btree*,int);
int sqlite3BtreeGetOptimalReserve(Btree*);
int sqlite3BtreeGetReserveNoMutex(Btree *p);
int sqlite3BtreeSetAutoVacuum(Btree *, int);
int sqlite3BtreeGetAutoVacuum(Btree *);
int sqlite3BtreeBeginTrans(Btree*,int);
int sqlite3BtreeCommitPhaseOne(Btree*, const char *zMaster);
int sqlite3BtreeCommitPhaseTwo(Btree*, int);
int sqlite3BtreeCommit(Btree*);
int sqlite3BtreeRollback(Btree*,int,int);
int sqlite3BtreeBeginStmt(Btree*,int);
int sqlite3BtreeCreateTable(Btree*, int*, int flags);
int sqlite3BtreeIsInTrans(Btree*);
int sqlite3BtreeIsInReadTrans(Btree*);
int sqlite3BtreeIsInBackup(Btree*);
void *sqlite3BtreeSchema(Btree *, int, void(*)(void *));
int sqlite3BtreeSchemaLocked(Btree *pBtree);
int sqlite3BtreeLockTable(Btree *pBtree, int iTab, u8 isWriteLock);
int sqlite3BtreeSavepoint(Btree *, int, int);
int sqlite3BtreeFileFormat(Btree *);
const char *sqlite3BtreeGetFilename(Btree *);
const char *sqlite3BtreeGetJournalname(Btree *);
int sqlite3BtreeCopyFile(Btree *, Btree *);
int sqlite3BtreeIncrVacuum(Btree *);
/* The flags parameter to sqlite3BtreeCreateTable can be the bitwise OR
** of the flags shown below.
**
** Every SQLite table must have either BTREE_INTKEY or BTREE_BLOBKEY set.
** With BTREE_INTKEY, the table key is a 64-bit integer and arbitrary data
** is stored in the leaves. (BTREE_INTKEY is used for SQL tables.) With
** BTREE_BLOBKEY, the key is an arbitrary BLOB and no content is stored
** anywhere - the key is the content. (BTREE_BLOBKEY is used for SQL
** indices.)
*/
#define BTREE_INTKEY 1 /* Table has only 64-bit signed integer keys */
#define BTREE_BLOBKEY 2 /* Table has keys only - no data */
int sqlite3BtreeDropTable(Btree*, int, int*);
int sqlite3BtreeClearTable(Btree*, int, int*);
int sqlite3BtreeClearTableOfCursor(BtCursor*);
int sqlite3BtreeTripAllCursors(Btree*, int, int);
void sqlite3BtreeGetMeta(Btree *pBtree, int idx, u32 *pValue);
int sqlite3BtreeUpdateMeta(Btree*, int idx, u32 value);
int sqlite3BtreeNewDb(Btree *p);
/*
** The second parameter to sqlite3BtreeGetMeta or sqlite3BtreeUpdateMeta
** should be one of the following values. The integer values are assigned
** to constants so that the offset of the corresponding field in an
** SQLite database header may be found using the following formula:
**
** offset = 36 + (idx * 4)
**
** For example, the free-page-count field is located at byte offset 36 of
** the database file header. The incr-vacuum-flag field is located at
** byte offset 64 (== 36+4*7).
**
** The BTREE_DATA_VERSION value is not really a value stored in the header.
** It is a read-only number computed by the pager. But we merge it with
** the header value access routines since its access pattern is the same.
** Call it a "virtual meta value".
*/
#define BTREE_FREE_PAGE_COUNT 0
#define BTREE_SCHEMA_VERSION 1
#define BTREE_FILE_FORMAT 2
#define BTREE_DEFAULT_CACHE_SIZE 3
#define BTREE_LARGEST_ROOT_PAGE 4
#define BTREE_TEXT_ENCODING 5
#define BTREE_USER_VERSION 6
#define BTREE_INCR_VACUUM 7
#define BTREE_APPLICATION_ID 8
#define BTREE_DATA_VERSION 15 /* A virtual meta-value */
/*
** An instance of the following structure holds information about a
** single index record that has already been parsed out into individual
** values.
**
** A record is an object that contains one or more fields of data.
** Records are used to store the content of a table row and to store
** the key of an index. A blob encoding of a record is created by
** the OP_MakeRecord opcode of the VDBE and is disassembled by the
** OP_Column opcode.
**
** This structure holds a record that has already been disassembled
** into its constituent fields.
**
** The r1 and r2 member variables are only used by the optimized comparison
** functions vdbeRecordCompareInt() and vdbeRecordCompareString().
*/
struct UnpackedRecord {
KeyInfo *pKeyInfo; /* Collation and sort-order information */
u16 nField; /* Number of entries in apMem[] */
i8 default_rc; /* Comparison result if keys are equal */
u8 errCode; /* Error detected by xRecordCompare (CORRUPT or NOMEM) */
Mem *aMem; /* Values */
int r1; /* Value to return if (lhs > rhs) */
int r2; /* Value to return if (rhs < lhs) */
};
/* One or more of the following flags are set to indicate the validOK
** representations of the value stored in the Mem struct.
**
** If the MEM_Null flag is set, then the value is an SQL NULL value.
** No other flags may be set in this case.
**
** If the MEM_Str flag is set then Mem.z points at a string representation.
** Usually this is encoded in the same unicode encoding as the main
** database (see below for exceptions). If the MEM_Term flag is also
** set, then the string is nul terminated. The MEM_Int and MEM_Real
** flags may coexist with the MEM_Str flag.
*/
#define MEM_Null 0x0001 /* Value is NULL */
#define MEM_Str 0x0002 /* Value is a string */
#define MEM_Int 0x0004 /* Value is an integer */
#define MEM_Real 0x0008 /* Value is a real number */
#define MEM_Blob 0x0010 /* Value is a BLOB */
#define MEM_Term 0x0200 /* String rep is nul terminated */
#define MEM_Dyn 0x0400 /* Need to call Mem.xDel() on Mem.z */
#define MEM_Static 0x0800 /* Mem.z points to a static string */
#define MEM_Ephem 0x1000 /* Mem.z points to an ephemeral string */
#define MEM_Zero 0x4000 /* Mem.i contains count of 0s appended to blob */
/*
** Internally, the vdbe manipulates nearly all SQL values as Mem
** structures. Each Mem struct may cache multiple representations (string,
** integer etc.) of the same value.
*/
struct Mem {
union MemValue {
double r; /* Real value used when MEM_Real is set in flags */
i64 i; /* Integer value used when MEM_Int is set in flags */
int nZero; /* Used when bit MEM_Zero is set in flags */
} u;
u16 flags; /* Some combination of MEM_Null, MEM_Str, MEM_Dyn, etc. */
u8 enc; /* SQLITE_UTF8, SQLITE_UTF16BE, SQLITE_UTF16LE */
u8 eSubtype; /* Subtype for this value */
int n; /* Number of characters in string value, excluding '\0' */
char *z; /* String or BLOB value */
/* ShallowCopy only needs to copy the information above */
char *zMalloc; /* Space to hold MEM_Str or MEM_Blob if szMalloc>0 */
int szMalloc; /* Size of the zMalloc allocation */
u32 uTemp; /* Transient storage for serial_type in OP_MakeRecord */
Btree *pBtree; /* The associated database connection */
void (*xDel)(void*);/* Destructor for Mem.z - only valid if MEM_Dyn */
#ifdef SQLITE_DEBUG
Mem *pScopyFrom; /* This Mem is a shallow copy of pScopyFrom */
void *pFiller; /* So that sizeof(Mem) is a multiple of 8 */
#endif
};
/*
** Values that may be OR'd together to form the second argument of an
** sqlite3BtreeCursorHints() call.
**
** The BTREE_BULKLOAD flag is set on index cursors when the index is going
** to be filled with content that is already in sorted order.
**
** The BTREE_SEEK_EQ flag is set on cursors that will get OP_SeekGE or
** OP_SeekLE opcodes for a range search, but where the range of entries
** selected will all have the same key. In other words, the cursor will
** be used only for equality key searches.
**
*/
#define BTREE_BULKLOAD 0x00000001 /* Used to full index in sorted order */
#define BTREE_SEEK_EQ 0x00000002 /* EQ seeks only - no range seeks */
int sqlite3BtreeCursor(
Btree*, /* BTree containing table to open */
int iTable, /* Index of root page */
int wrFlag, /* 1 for writing. 0 for read-only */
int N, int X, /* index of N key columns and X extra columns */
BtCursor **ppCursor /* Space to write cursor pointer */
);
int sqlite3BtreeCursorSize(void);
int sqlite3BtreeCloseCursor(BtCursor*);
void sqlite3BtreeInitUnpackedRecord(
UnpackedRecord *pUnKey,
BtCursor* pCur,
int nField,
int default_rc,
Mem* pMem);
int sqlite3BtreeMovetoUnpacked(
BtCursor*,
UnpackedRecord *pUnKey,
i64 intKey,
int bias,
int *pRes
);
int sqlite3BtreeCursorHasMoved(BtCursor*);
int sqlite3BtreeCursorRestore(BtCursor*, int*);
int sqlite3BtreeDelete(BtCursor*, int);
int sqlite3BtreeInsert(BtCursor*, const void *pKey, i64 nKey,
const void *pData, int nData,
int nZero, int bias, int seekResult);
int sqlite3BtreeFirst(BtCursor*, int *pRes);
int sqlite3BtreeLast(BtCursor*, int *pRes);
int sqlite3BtreeNext(BtCursor*, int *pRes);
int sqlite3BtreeEof(BtCursor*);
int sqlite3BtreePrevious(BtCursor*, int *pRes);
int sqlite3BtreeKeySize(BtCursor*, i64 *pSize);
int sqlite3BtreeKey(BtCursor*, u32 offset, u32 amt, void*);
const void *sqlite3BtreeKeyFetch(BtCursor*, u32 *pAmt);
const void *sqlite3BtreeDataFetch(BtCursor*, u32 *pAmt);
int sqlite3BtreeDataSize(BtCursor*, u32 *pSize);
int sqlite3BtreeData(BtCursor*, u32 offset, u32 amt, void*);
char *sqlite3BtreeIntegrityCheck(Btree*, int *aRoot, int nRoot, int, int*);
struct Pager *sqlite3BtreePager(Btree*);
int sqlite3BtreePutData(BtCursor*, u32 offset, u32 amt, void*);
void sqlite3BtreeIncrblobCursor(BtCursor *);
void sqlite3BtreeClearCursor(BtCursor *);
int sqlite3BtreeSetVersion(Btree *pBt, int iVersion);
void sqlite3BtreeCursorHints(BtCursor *, unsigned int mask);
#ifdef SQLITE_DEBUG
int sqlite3BtreeCursorHasHint(BtCursor*, unsigned int mask);
#endif
int sqlite3BtreeIsReadonly(Btree *pBt);
#ifndef NDEBUG
int sqlite3BtreeCursorIsValid(BtCursor*);
#endif
#ifndef SQLITE_OMIT_BTREECOUNT
int sqlite3BtreeCount(BtCursor *, i64 *);
#endif
#ifdef SQLITE_TEST
int sqlite3BtreeCursorInfo(BtCursor*, int*, int);
void sqlite3BtreeCursorList(Btree*);
#endif
#ifndef SQLITE_OMIT_WAL
int sqlite3BtreeCheckpoint(Btree*, int, int *, int *);
#endif
/*
** If we are not using shared cache, then there is no need to
** use mutexes to access the BtShared structures. So make the
** Enter and Leave procedures no-ops.
*/
#ifndef SQLITE_OMIT_SHARED_CACHE
void sqlite3BtreeEnter(Btree*);
#else
# define sqlite3BtreeEnter(X)
#endif
#if !defined(SQLITE_OMIT_SHARED_CACHE) && SQLITE_THREADSAFE
int sqlite3BtreeSharable(Btree*);
void sqlite3BtreeLeave(Btree*);
void sqlite3BtreeEnterCursor(BtCursor*);
void sqlite3BtreeLeaveCursor(BtCursor*);
#else
# define sqlite3BtreeSharable(X) 0
# define sqlite3BtreeLeave(X)
# define sqlite3BtreeEnterCursor(X)
# define sqlite3BtreeLeaveCursor(X)
#endif
u32 sqlite3BtreeSerialType(Mem *pMem, int file_format);
u32 sqlite3BtreeSerialTypeLen(u32);
u32 sqlite3BtreeSerialGet(const unsigned char*, u32, Mem *);
u32 sqlite3BtreeSerialPut(u8*, Mem*, u32);
/*
** Routines to read and write variable-length integers. These used to
** be defined locally, but now we use the varint routines in the util.c
** file.
*/
int sqlite3BtreePutVarint(unsigned char*, u64);
u8 sqlite3BtreeGetVarint(const unsigned char *, u64 *);
u8 sqlite3BtreeGetVarint32(const unsigned char *, u32 *);
int sqlite3BtreeVarintLen(u64 v);
/*
** The common case is for a varint to be a single byte. They following
** macros handle the common case without a procedure call, but then call
** the procedure for larger varints.
*/
#define getVarint32(A,B) \
(u8)((*(A)<(u8)0x80)?((B)=(u32)*(A)),1:sqlite3BtreeGetVarint32((A),(u32 *)&(B)))
#define putVarint32(A,B) \
(u8)(((u32)(B)<(u32)0x80)?(*(A)=(unsigned char)(B)),1:\
sqlite3BtreePutVarint((A),(B)))
#define getVarint sqlite3BtreeGetVarint
#define putVarint sqlite3BtreePutVarint
int sqlite3BtreeIdxRowid(Btree*, BtCursor*, i64*);
int sqlite3BtreeRecordCompare(int,const void*,UnpackedRecord*);
const char *sqlite3BtreeErrName(int rc);
#endif /* _BTREE_H_ */