commit fd187edbafff4507f2f173cc2bc2948658334e55 Author: Allen Webster Date: Fri Oct 17 15:49:52 2025 -0700 lesson-1 initial commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..07ed706 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +build/* \ No newline at end of file diff --git a/aritynode.blank.c b/aritynode.blank.c new file mode 100644 index 0000000..9d654bd --- /dev/null +++ b/aritynode.blank.c @@ -0,0 +1,49 @@ +//////////////////////////////// +// Functions: Arity Node + +// construction + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_empty(Arena *arena){ + return(0); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_singleton(Arena *arena){ + return(0); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_arrow(Arena *arena, DS_ArityNode *domain, DS_ArityNode *codomain){ + return(0); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_paste(Arena *arena, DS_ArityNode *a, DS_ArityNode *b){ + return(0); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_sum(Arena *arena, ...){ + va_list args; + va_start(args, arena); + va_end(args); + return(0); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_ktuple(Arena *arena, U32 coefficient){ + return(0); +} + +// operations + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_copy(Arena *arena, DS_ArityNode *arity){ + return(0); +} + +MR4TH_SYMBOL B32 +ds_aritynode_equal(DS_ArityNode *a, DS_ArityNode *b){ + return(0); +} diff --git a/aritynode.c b/aritynode.c new file mode 100644 index 0000000..ba43a07 --- /dev/null +++ b/aritynode.c @@ -0,0 +1,359 @@ +//////////////////////////////// +// Functions: Arity Node + +// construction + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_empty(Arena *arena){ + DS_ArityNode *node = push_array(arena, DS_ArityNode, 1); + node->kind = DS_ArityKind_Empty; + return(node); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_singleton(Arena *arena){ + DS_ArityNode *node = push_array(arena, DS_ArityNode, 1); + node->kind = DS_ArityKind_Singleton; + node->coefficient = 1; + return(node); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_arrow(Arena *arena, DS_ArityNode *domain, DS_ArityNode *codomain){ + DS_ArityNode *node = 0; + if (domain->kind == DS_ArityKind_Empty || + codomain->kind == DS_ArityKind_Empty){ + node = codomain; + } + else{ + node = push_array(arena, DS_ArityNode, 1); + node->kind = DS_ArityKind_Arrow; + node->coefficient = 1; + node->arrow.domain = domain; + node->arrow.codomain = codomain; + } + return(node); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_paste(Arena *arena, DS_ArityNode *a, DS_ArityNode *b){ + ArenaTemp scratch = arena_get_scratch(&arena, 1); + DS_ArityNode *node = 0; + + if (a->kind == DS_ArityKind_Empty){ + node = b; + } + else if (b->kind == DS_ArityKind_Empty){ + node = a; + } + else{ + // count parts + U64 max_part_count = 0; + if (a->kind != DS_ArityKind_Tuple){ + max_part_count += 1; + } + else{ + max_part_count += a->tuple.part_count; + } + if (b->kind != DS_ArityKind_Tuple){ + max_part_count += 1; + } + else{ + max_part_count += b->tuple.part_count; + } + + // fill parts + DS_ArityNode **parts = push_array(scratch.arena, DS_ArityNode*, max_part_count); + DS_ArityNode **part_ptr = parts; + + if (a->kind != DS_ArityKind_Tuple){ + *part_ptr = ds_aritynode__part_copy(arena, a); + (*part_ptr)->coefficient = 1; + part_ptr += 1; + } + else{ + for (U64 i = 0; i < a->tuple.part_count; i += 1){ + DS_ArityNode *a_part = a->tuple.parts[i]; + *part_ptr = ds_aritynode__part_copy(arena, a_part); + (*part_ptr)->coefficient = a_part->coefficient; + part_ptr += 1; + } + } + + if (b->kind != DS_ArityKind_Tuple){ + DS_ArityNode *match_pos = ds_aritynode__part_find_match(parts, part_ptr, b); + if (match_pos != 0){ + match_pos->coefficient += 1; + } + else{ + *part_ptr = ds_aritynode__part_copy(arena, b); + (*part_ptr)->coefficient = 1; + part_ptr += 1; + } + } + else{ + for (U64 j = 0; j < b->tuple.part_count; j += 1){ + DS_ArityNode *b_part = b->tuple.parts[j]; + DS_ArityNode *match_pos = ds_aritynode__part_find_match(parts, part_ptr, b_part); + if (match_pos != 0){ + match_pos->coefficient += b_part->coefficient; + } + else{ + *part_ptr = ds_aritynode__part_copy(arena, b_part); + (*part_ptr)->coefficient = b_part->coefficient; + part_ptr += 1; + } + } + } + + // final part count + U64 part_count = (U64)(part_ptr - parts); + + // fill result node + Assert(part_count > 1 || + part_count == 1 && parts[0]->coefficient > 1); + + DS_ArityNode **parts_final = push_array(arena, DS_ArityNode*, part_count); + MemoryCopy(parts_final, parts, sizeof(*parts)*part_count); + + node = push_array(arena, DS_ArityNode, 1); + node->kind = DS_ArityKind_Tuple; + node->coefficient = 1; + node->tuple.parts = parts_final; + node->tuple.part_count = part_count; + } + + arena_release_scratch(&scratch); + + return(node); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_sum(Arena *arena, ...){ + va_list args; + va_start(args, arena); + + va_list args2; + va_copy(args2, args); + + ArenaTemp scratch = arena_get_scratch(&arena, 1); + + // count parts + U64 max_part_count = 0; + for (;;){ + U32 multiplier = va_arg(args, U32); + if (multiplier == 0){ + break; + } + DS_ArityNode *arity = va_arg(args, DS_ArityNode*); + if (arity->kind == DS_ArityKind_Empty){ + // do nothing + } + else if (arity->kind != DS_ArityKind_Tuple){ + max_part_count += 1; + } + else{ + max_part_count += arity->tuple.part_count; + } + } + + // fill parts + DS_ArityNode **parts = push_array(scratch.arena, DS_ArityNode*, max_part_count); + DS_ArityNode **part_ptr = parts; + + for (;;){ + U32 multiplier = va_arg(args2, U32); + if (multiplier == 0){ + break; + } + DS_ArityNode *arity = va_arg(args2, DS_ArityNode*); + + if (arity->kind == DS_ArityKind_Empty){ + // do nothing + } + else if (arity->kind != DS_ArityKind_Tuple){ + DS_ArityNode *match_pos = ds_aritynode__part_find_match(parts, part_ptr, arity); + if (match_pos != 0){ + match_pos->coefficient += multiplier; + } + else{ + *part_ptr = ds_aritynode__part_copy(arena, arity); + (*part_ptr)->coefficient = multiplier; + part_ptr += 1; + } + } + else{ + for (U64 j = 0; j < arity->tuple.part_count; j += 1){ + DS_ArityNode *b_part = arity->tuple.parts[j]; + DS_ArityNode *match_pos = ds_aritynode__part_find_match(parts, part_ptr, b_part); + if (match_pos != 0){ + match_pos->coefficient += multiplier*b_part->coefficient; + } + else{ + *part_ptr = ds_aritynode__part_copy(arena, b_part); + (*part_ptr)->coefficient = multiplier*b_part->coefficient; + part_ptr += 1; + } + } + } + } + + // final part count + U64 part_count = (U64)(part_ptr - parts); + + // fill result node + DS_ArityNode *node = 0; + if (part_count == 0){ + node = ds_aritynode_empty(arena); + } + else if (part_count == 1 && + parts[0]->coefficient == 1){ + node = parts[0]; + } + else{ + DS_ArityNode **parts_final = push_array(arena, DS_ArityNode*, part_count); + MemoryCopy(parts_final, parts, sizeof(*parts)*part_count); + + node = push_array(arena, DS_ArityNode, 1); + node->kind = DS_ArityKind_Tuple; + node->coefficient = 1; + node->tuple.parts = parts_final; + node->tuple.part_count = part_count; + } + + arena_release_scratch(&scratch); + + va_end(args2); + va_end(args); + + return(node); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_ktuple(Arena *arena, U32 coefficient){ + DS_ArityNode *result = 0; + + if (coefficient > 1){ + result = push_array(arena, DS_ArityNode, 1); + DS_ArityNode **parts = push_array(arena, DS_ArityNode*, 1); + DS_ArityNode *singleton = push_array(arena, DS_ArityNode, 1); + + result->kind = DS_ArityKind_Tuple; + result->coefficient = 1; + result->tuple.parts = parts; + result->tuple.part_count = 1; + + parts[0] = singleton; + + singleton->kind = DS_ArityKind_Singleton; + singleton->coefficient = coefficient; + } + else if (coefficient == 1){ + result = ds_aritynode_singleton(arena); + } + else{ + result = ds_aritynode_empty(arena); + } + + return(result); +} + +// operations + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode_copy(Arena *arena, DS_ArityNode *arity){ + DS_ArityNode *result = push_array(arena, DS_ArityNode, 1); + result->kind = arity->kind; + result->coefficient = arity->coefficient; + switch (result->kind){ + case DS_ArityKind_Arrow: + { + result->arrow.domain = ds_aritynode_copy(arena, arity->arrow.domain); + result->arrow.codomain = ds_aritynode_copy(arena, arity->arrow.codomain); + }break; + + case DS_ArityKind_Tuple: + { + U64 part_count = arity->tuple.part_count; + DS_ArityNode **parts = push_array(arena, DS_ArityNode*, part_count); + for (U64 i = 0; i < part_count; i += 1){ + parts[i] = ds_aritynode_copy(arena, arity->tuple.parts[i]); + } + result->tuple.parts = parts; + result->tuple.part_count = part_count; + }break; + } + return(result); +} + +MR4TH_SYMBOL B32 +ds_aritynode_equal(DS_ArityNode *a, DS_ArityNode *b){ + B32 result = 0; + + if (a->kind == b->kind){ + switch (a->kind){ + case DS_ArityKind_Empty: + case DS_ArityKind_Singleton: result = 1; break; + + case DS_ArityKind_Arrow: + { + if (ds_aritynode_equal(a->arrow.domain, b->arrow.domain) && + ds_aritynode_equal(a->arrow.codomain, b->arrow.codomain)){ + result = 1; + } + }break; + + case DS_ArityKind_Tuple: + { + if (a->tuple.part_count == b->tuple.part_count){ + result = 1; + for (U64 i = 0; i < a->tuple.part_count; i += 1){ + DS_ArityNode *a_part = a->tuple.parts[i]; + B32 found_match = 0; + for (U64 j = 0; j < b->tuple.part_count; j += 1){ + DS_ArityNode *b_part = b->tuple.parts[j]; + if (b_part->coefficient == a_part->coefficient && + ds_aritynode_equal(a_part, b_part)){ + found_match = 1; + break; + } + } + if (!found_match){ + result = 0; + break; + } + } + } + }break; + } + } + + return(result); +} + +// helpers + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode__part_copy(Arena *arena, DS_ArityNode *node){ + Assert(node->kind != DS_ArityKind_Tuple); + DS_ArityNode *result = push_array(arena, DS_ArityNode, 1); + result->kind = node->kind; + if (result->kind == DS_ArityKind_Arrow){ + result->arrow.domain = node->arrow.domain; + result->arrow.codomain = node->arrow.codomain; + } + return(result); +} + +MR4TH_SYMBOL DS_ArityNode* +ds_aritynode__part_find_match(DS_ArityNode **parts_first, DS_ArityNode **parts_opl, DS_ArityNode *key){ + DS_ArityNode **part = parts_first; + DS_ArityNode *match = 0; + for (; part < parts_opl; part += 1){ + if (ds_aritynode_equal(*part, key)){ + match = *part; + break; + } + } + return(match); +} diff --git a/aritynode.h b/aritynode.h new file mode 100644 index 0000000..91a345b --- /dev/null +++ b/aritynode.h @@ -0,0 +1,92 @@ +#ifndef ARITYNODE_H +#define ARITYNODE_H + +//////////////////////////////// +// Type: Arity Node + +typedef enum DS_ArityKind{ + DS_ArityKind_Empty = 0, + DS_ArityKind_Singleton = 1, + DS_ArityKind_Arrow = 2, + DS_ArityKind_Tuple = 3, +} DS_ArityKind; + +typedef struct DS_ArityNode{ + DS_ArityKind kind; + U32 coefficient; + union{ + struct{ + struct DS_ArityNode *domain; + struct DS_ArityNode *codomain; + } arrow; + struct{ + struct DS_ArityNode **parts; + U64 part_count; + } tuple; + }; +} DS_ArityNode; + +//////////////////////////////// +// Functions: Arity Node + +// construction + +/* NOTE: +** Construction functions that take in arity node(s) require +** that the arena that allocated the input arity node(s) +** is the same arena that is used in the current call, and +** that the arena has not popped the nodes. +** +** Example of misuse: +** +** GIVEN Arena *a1; Arena *a2; +** WITH (a1 != a2): +** DS_ArityNode *n1 = ds_aritynode_singleton(a1); +** DS_ArityNode *n2 = ds_aritynode_arrow(a2, n1); @bad - changing arenas +** +** Why this matters: +** +** We don't want to have to deep copy every node we ever see as input, +** so construction functions just keep pointers to their inputs, or +** sometimes make shallow copies but still keep the original versions +** of the deeper nodes. Because of the way arenas work, if these +** all exist on one arena, later nodes always point towards earlier +** nodes, and so if a node is still on the arena, so are all of the nodes +** that it depends on. However, if we start crossing arenas, we would +** have to be much more careful not to start generating use-after-free +** issues. +** +** If you think it through and you *know what you're doing* you can +** break this rule, but as a rule of thumb, it usually works best if you +** can put all the nodes that work together into the same arena. +*/ + +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_empty(Arena *arena); +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_singleton(Arena *arena); +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_arrow(Arena *arena, DS_ArityNode *domain, DS_ArityNode *codomain); +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_paste(Arena *arena, DS_ArityNode *a, DS_ArityNode *b); + +/* NOTE: +** ds_aritynode_sum takes the variadic layout: +** (coeff_1:U32, arity_1:DS_ArityNode*, ..., coeff_k:U32, arity_k:DS_ArityNode*, 0) +*/ +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_sum(Arena *arena, ...); + +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_ktuple(Arena *arena, U32 coefficient); + +// operations + +/* NOTE: + ** ds_aritynode_copy is not a "construction function" +** it can deep copy an arity node from one arena to another. +*/ +MR4TH_SYMBOL DS_ArityNode* ds_aritynode_copy(Arena *arena, DS_ArityNode *arity); + +MR4TH_SYMBOL B32 ds_aritynode_equal(DS_ArityNode *a, DS_ArityNode *b); + +// helpers + +MR4TH_SYMBOL DS_ArityNode* ds_aritynode__part_copy(Arena *arena, DS_ArityNode *node); +MR4TH_SYMBOL DS_ArityNode* ds_aritynode__part_find_match(DS_ArityNode **parts_first, DS_ArityNode **parts_opl, DS_ArityNode *key); + +#endif //ARITYNODE_H diff --git a/aritynode.test.c b/aritynode.test.c new file mode 100644 index 0000000..5649701 --- /dev/null +++ b/aritynode.test.c @@ -0,0 +1,57 @@ +//////////////////////////////// +// Arity Node Sanity Test Function + +MR4TH_SYMBOL void +ds_aritynode__test(void){ + ArenaTemp scratch = arena_get_scratch(0, 0); + + DS_ArityNode *a_empty = ds_aritynode_empty(scratch.arena); + DS_ArityNode *a_s1 = ds_aritynode_singleton(scratch.arena); + DS_ArityNode *a_s2 = ds_aritynode_paste(scratch.arena, a_s1, a_s1); + DS_ArityNode *a_s3 = ds_aritynode_paste(scratch.arena, a_s2, a_s1); + DS_ArityNode *a_ar1 = ds_aritynode_arrow(scratch.arena, a_s1, a_s1); + + Assert(ds_aritynode_equal(a_empty, a_empty)); + Assert(ds_aritynode_equal(a_s1, a_s1)); + Assert(ds_aritynode_equal(a_s2, a_s2)); + Assert(ds_aritynode_equal(a_s3, a_s3)); + Assert(ds_aritynode_equal(a_ar1, a_ar1)); + + Assert(!ds_aritynode_equal(a_empty, a_s1)); + Assert(!ds_aritynode_equal(a_s1, a_s2)); + Assert(!ds_aritynode_equal(a_ar1, a_s1)); + + DS_ArityNode *a_s2x = ds_aritynode_sum(scratch.arena, 2, a_s1, 0); + DS_ArityNode *a_s3x = ds_aritynode_sum(scratch.arena, 3, a_s1, 0); + + Assert(ds_aritynode_equal(a_s2, a_s2x)); + Assert(ds_aritynode_equal(a_s3, a_s3x)); + + DS_ArityNode *a_s1_ar1 = ds_aritynode_paste(scratch.arena, a_s1, a_ar1); + DS_ArityNode *a_s2_ar1 = ds_aritynode_paste(scratch.arena, a_s1_ar1, a_s1); + DS_ArityNode *a_s2_ar1_x = ds_aritynode_paste(scratch.arena, a_s2, a_ar1); + + Assert(ds_aritynode_equal(a_s2_ar1, a_s2_ar1_x)); + + DS_ArityNode *a_ar1_2 = ds_aritynode_arrow(scratch.arena, a_s1, a_s2); + DS_ArityNode *a_ar1_3 = ds_aritynode_arrow(scratch.arena, a_s1, a_s3); + DS_ArityNode *a_ar_ar1 = ds_aritynode_arrow(scratch.arena, a_ar1, a_ar1); + DS_ArityNode *a_ar_ar2 = ds_aritynode_arrow(scratch.arena, a_ar1, a_ar1_2); + DS_ArityNode *a_ar_ar3 = ds_aritynode_arrow(scratch.arena, a_ar1, a_ar1_3); + + Assert(!ds_aritynode_equal(a_ar1, a_ar_ar1)); + Assert(!ds_aritynode_equal(a_ar_ar1, a_ar_ar2)); + Assert(!ds_aritynode_equal(a_ar_ar1, a_ar_ar3)); + Assert(!ds_aritynode_equal(a_ar_ar2, a_ar_ar3)); + + DS_ArityNode *a_ar1x = ds_aritynode_sum(scratch.arena, 1, a_ar1, 3, a_empty, 1, a_empty, 0); + + Assert(ds_aritynode_equal(a_ar1, a_ar1x)); + + DS_ArityNode *a_s17 = ds_aritynode_sum(scratch.arena, 17, a_s1, 0); + DS_ArityNode *a_s17x = ds_aritynode_ktuple(scratch.arena, 17); + + Assert(ds_aritynode_equal(a_s17, a_s17x)); + + arena_release_scratch(&scratch); +} diff --git a/base.c b/base.c new file mode 100644 index 0000000..13eb47d --- /dev/null +++ b/base.c @@ -0,0 +1,2260 @@ +//////////////////////////////// +// Memory Configuration + +#define MR4TH_MEM_DEFAULT_RESERVE_SIZE GB(1) +#define MR4TH_MEM_COMMIT_BLOCK_SIZE MB(64) +#define MR4TH_MEM_MAX_ALIGN 64 +#define MR4TH_MEM_SCRATCH_POOL_COUNT 2 + +//////////////////////////////// +// Functions: Arena + +#define MEM_INITIAL_COMMIT KB(4) +#define MEM_INTERNAL_MIN_SIZE AlignUpPow2(sizeof(Arena), MR4TH_MEM_MAX_ALIGN) + +// arena implementation + +MR4TH_SYMBOL Arena* +arena_alloc_reserve(U64 reserve_size, B32 growing){ + Arena *result = 0; + if (reserve_size >= MEM_INITIAL_COMMIT){ + void *memory = os_memory_reserve(reserve_size); + if (os_memory_commit(memory, MEM_INITIAL_COMMIT)){ + result = (Arena*)memory; + result->current = result; + result->prev = 0; + result->alignment = sizeof(void*); + result->growing = growing; + result->base_pos = 0; + result->chunk_cap = reserve_size; + result->chunk_pos = MEM_INTERNAL_MIN_SIZE; + result->chunk_commit_pos = MEM_INITIAL_COMMIT; + } + } + Assert(result != 0); + return(result); +} + +MR4TH_SYMBOL Arena* +arena_alloc(void){ + Arena *result = arena_alloc_reserve(MR4TH_MEM_DEFAULT_RESERVE_SIZE, 1); + return(result); +} + +MR4TH_SYMBOL void +arena_release(Arena *arena){ + Arena *ptr = arena->current; + for (;ptr != 0;){ + Arena *prev = ptr->prev; + os_memory_release(ptr, ptr->chunk_cap); + ptr = prev; + } +} + +MR4TH_SYMBOL void* +arena_push_no_zero(Arena *arena, U64 size){ + void *result = 0; + + Arena *current = arena->current; + + // allocate new chunk if necessary + if (arena->growing){ + U64 next_chunk_pos = AlignUpPow2(current->chunk_pos, arena->alignment); + next_chunk_pos += size; + if (next_chunk_pos > current->chunk_cap){ + U64 new_reserve_size = MR4TH_MEM_DEFAULT_RESERVE_SIZE; + U64 enough_to_fit = size + MEM_INTERNAL_MIN_SIZE; + if (new_reserve_size < enough_to_fit){ + new_reserve_size = AlignUpPow2(enough_to_fit, KB(4)); + } + + void *memory = os_memory_reserve(new_reserve_size); + if (os_memory_commit(memory, MEM_INITIAL_COMMIT)){ + Arena *new_chunk = (Arena*)memory; + new_chunk->prev = current; + new_chunk->base_pos = current->base_pos + current->chunk_cap; + new_chunk->chunk_cap = new_reserve_size; + new_chunk->chunk_pos = MEM_INTERNAL_MIN_SIZE; + new_chunk->chunk_commit_pos = MEM_INITIAL_COMMIT; + current = arena->current = new_chunk; + } + } + } + + { + // if there is room in this chunk's reserve ... + U64 result_pos = AlignUpPow2(current->chunk_pos, arena->alignment); + U64 next_chunk_pos = result_pos + size; + if (next_chunk_pos <= current->chunk_cap){ + + // commit more memory if necessary + if (next_chunk_pos > current->chunk_commit_pos){ + U64 next_commit_pos_aligned = + AlignUpPow2(next_chunk_pos, MR4TH_MEM_COMMIT_BLOCK_SIZE); + U64 next_commit_pos = + ClampTop(next_commit_pos_aligned, current->chunk_cap); + U64 commit_size = next_commit_pos - current->chunk_commit_pos; + if (os_memory_commit((U8*)current + current->chunk_commit_pos, commit_size)){ + current->chunk_commit_pos = next_commit_pos; + } + } + + // if there is room in the commit range, return memory & advance pos + if (next_chunk_pos <= current->chunk_commit_pos){ + result = (U8*)current + result_pos; + current->chunk_pos = next_chunk_pos; + } + } + } + + return(result); +} + +MR4TH_SYMBOL void +arena_pop_to(Arena *arena, U64 pos){ + Arena *current = arena->current; + U64 total_pos = current->base_pos + current->chunk_pos; + if (pos < total_pos){ + // release all chunks that begin after this pos + U64 clamped_total_pos = ClampBot(pos, MEM_INTERNAL_MIN_SIZE); + for (; clamped_total_pos < current->base_pos; ){ + Arena *prev = current->prev; + os_memory_release(current, current->chunk_cap); + current = prev; + } + + // update arena's current + { + arena->current = current; + } + + // update the chunk position of the chunk in + // the chain that contains this position. + { + U64 chunk_pos = clamped_total_pos - current->base_pos; + U64 clamped_chunk_pos = ClampBot(chunk_pos, MEM_INTERNAL_MIN_SIZE); + current->chunk_pos = clamped_chunk_pos; + } + } +} + +MR4TH_SYMBOL U64 +arena_current_pos(Arena *arena){ + Arena *current = arena->current; + U64 result = current->base_pos + current->chunk_pos; + return(result); +} + +MR4TH_SYMBOL void* +arena_push(Arena *arena, U64 size){ + void *result = arena_push_no_zero(arena, size); + MemoryZero(result, size); + return(result); +} + +MR4TH_SYMBOL void +arena_align(Arena *arena, U64 pow2_align){ + Assert(IsPow2OrZero(pow2_align) && pow2_align != 0 && + pow2_align <= MR4TH_MEM_MAX_ALIGN); + Arena *current = arena->current; + U64 p = current->chunk_pos; + U64 p_aligned = AlignUpPow2(p, pow2_align); + U64 z = p_aligned - p; + if (z > 0){ + arena_push(arena, z); + } +} + +MR4TH_SYMBOL void +arena_pop_amount(Arena *arena, U64 amount){ + Arena *current = arena->current; + U64 total_pos = current->base_pos + current->chunk_pos; + if (amount <= total_pos){ + U64 new_pos = total_pos - amount; + arena_pop_to(arena, new_pos); + } +} + +// temp helper functions + +MR4TH_SYMBOL ArenaTemp +arena_begin_temp(Arena *arena){ + U64 pos = arena_current_pos(arena); + ArenaTemp temp = {arena, pos}; + return(temp); +} + +MR4TH_SYMBOL void +arena_end_temp(ArenaTemp *temp){ + arena_pop_to(temp->arena, temp->pos); +} + +// scratch + +MR4TH_SYMBOL MR4TH_THREADVAR +Arena *arena__scratch_pool[MR4TH_MEM_SCRATCH_POOL_COUNT] = {0}; + +MR4TH_SYMBOL ArenaTemp +arena_get_scratch(Arena **conflict_array, U32 count){ + // init on first time + if (arena__scratch_pool[0] == 0){ + Arena **scratch_slot = arena__scratch_pool; + for (U64 i = 0; + i < MR4TH_MEM_SCRATCH_POOL_COUNT; + i += 1, scratch_slot += 1){ + *scratch_slot = arena_alloc(); + } + } + + // get non-conflicting arena + ArenaTemp result = {0}; + Arena **scratch_slot = arena__scratch_pool; + for (U64 i = 0; + i < MR4TH_MEM_SCRATCH_POOL_COUNT; + i += 1, scratch_slot += 1){ + B32 is_non_conflict = 1; + Arena **conflict_ptr = conflict_array; + for (U32 j = 0; j < count; j += 1, conflict_ptr += 1){ + if (*scratch_slot == *conflict_ptr){ + is_non_conflict = 0; + break; + } + } + if (is_non_conflict){ + result = arena_begin_temp(*scratch_slot); + break; + } + } + + return(result); +} + + +//////////////////////////////// +// Functions: Strings + +MR4TH_SYMBOL String8 +str8(U8 *str, U64 size){ + String8 result = {str, size}; + return(result); +} + +MR4TH_SYMBOL String8 +str8_range(U8 *first, U8 *opl){ + String8 result = {first, (U64)(opl - first)}; + return(result); +} + +MR4TH_SYMBOL String8 +str8_cstring(U8 *cstr){ + U8 *ptr = cstr; + for (;*ptr != 0; ptr += 1); + String8 result = str8_range(cstr, ptr); + return(result); +} + +MR4TH_SYMBOL String8 +str8_cstring_capped(U8 *cstr, U8 *opl){ + U8 *ptr = cstr; + for (;ptr < opl && *ptr != 0; ptr += 1); + String8 result = str8_range(cstr, ptr); + return(result); +} + +MR4TH_SYMBOL U32 +u32_from_str8_base10(String8 string){ + U32 result = 0; + + U8 *ptr = string.str; + U8 *opl = string.str + string.size; + for (; ptr < opl; ptr += 1){ + // extract + U8 num = 0xFF; + U8 s = *ptr - '0'; + if (s <= 9){ + num = s; + } + + // bad parse check + if (num >= 10){ + result = 0; + break; + } + + // increment result + result *= 10; + result += num; + } + + return(result); +} + + +//////////////////////////////// +// Functions: Stream + +// stream core implementation + +MR4TH_SYMBOL STREAM* +stream_new(void){ + Arena *arena = arena_alloc(); + STREAM *stream = push_array(arena, STREAM, 1); + stream->arena = arena; + stream->clear_pos = arena_current_pos(arena); + return(stream); +} + +MR4TH_SYMBOL void +stream_release(STREAM *stream){ + stream_clear(stream); +} + +MR4TH_SYMBOL void +stream_clear(STREAM *stream){ + Arena *arena = stream->arena; + U64 clear_pos = stream->clear_pos; + arena_pop_to(arena, clear_pos); + MemoryZeroStruct(stream); + stream->arena = arena; + stream->clear_pos = clear_pos; +} + +MR4TH_SYMBOL void +stream_write(STREAM *stream, String8 data){ + U64 data_pos = 0; + + for (;data_pos < data.size;){ + U64 remaining_size = data.size - data_pos; + + // try to get a node with buffer space from the stream + // (don't return a node with no space!) + STREAM_Node *node = 0; + { + if (stream->buffer_cap > 0){ + node = stream->last_node; + } + if (node != 0 && stream->buffer_cap <= node->size){ + node = 0; + } + } + + // if we didn't get a buffer, try the unused node + if (node == 0){ + if (stream->unused_node != 0){ + node = stream->unused_node; + stream->unused_node = 0; + stream->buffer_cap = node->size; + node->size = 0; + SLLQueuePush(stream->first_node, stream->last_node, node); + } + } + + // if we didn't get a buffer, make one now + if (node == 0){ + U64 alloc_size = sizeof(STREAM_Node) + remaining_size; + alloc_size = ClampBot(STREAM_ALLOC_SIZE, alloc_size); + + node = (STREAM_Node*)push_array_no_zero(stream->arena, U8, alloc_size); + SLLQueuePush(stream->first_node, stream->last_node, node); + node->size = 0; + + stream->buffer_cap = alloc_size - sizeof(STREAM_Node); + } + + // get buffer from the node + U8 *buffer = node->data + node->size; + U64 buffer_size = stream->buffer_cap - node->size; + + // calculate amount to copy + U64 copy_amount = ClampTop(remaining_size, buffer_size); + + // copy memory and increment counters + MemoryCopy(buffer, data.str + data_pos, copy_amount); + node->size += copy_amount; + stream->total_size += copy_amount; + data_pos += copy_amount; + } +} + +MR4TH_SYMBOL U8* +stream_allocate(STREAM *stream, U64 size){ + // try to get a node with buffer space + // (don't return a node with no space) + STREAM_Node *node = 0; + { + if (stream->buffer_cap > 0){ + node = stream->last_node; + } + if (node != 0 && stream->buffer_cap <= node->size){ + node = 0; + } + } + + // if there is a node but it's not big enough... + if (node != 0 && stream->buffer_cap - node->size < size){ + U64 remaining_cap = stream->buffer_cap - node->size; + U64 unused_ptr = IntFromPtr(node->data) + node->size; + U64 unused_opl = IntFromPtr(node->data) + stream->buffer_cap; + U64 unused_ptr_aligned = AlignUpPow2(unused_ptr, sizeof(void*)); + if (unused_opl > unused_ptr_aligned && + unused_opl - unused_ptr_aligned >= sizeof(STREAM_Node) + 32){ + STREAM_Node *unused_node = (STREAM_Node*)PtrFromInt(unused_ptr_aligned); + U64 leftover_buffer_size = unused_opl - unused_ptr_aligned - sizeof(STREAM_Node); + unused_node->size = leftover_buffer_size; + SLLStackPush(stream->unused_node, unused_node); + } + node = 0; + } + + // if we don't have a node then setup a new node with sufficient space. + if (node == 0){ + U64 alloc_size = sizeof(STREAM_Node) + size; + alloc_size = ClampBot(STREAM_ALLOC_SIZE, alloc_size); + + node = (STREAM_Node*)push_array_no_zero(stream->arena, U8, alloc_size); + SLLQueuePush(stream->first_node, stream->last_node, node); + node->size = 0; + + stream->buffer_cap = alloc_size - sizeof(STREAM_Node); + } + + // return the buffer + U8 *result = node->data + node->size; + node->size += size; + stream->total_size += size; + return(result); +} + +MR4TH_SYMBOL U64 +stream_total_size(STREAM *stream){ + return(stream->total_size); +} + +MR4TH_SYMBOL STREAM_Handle* +stream_next_chunk(STREAM *stream, STREAM_Handle *handle, String8 *chunk_out){ + STREAM_Node *node = (STREAM_Node*)handle; + if (node == 0){ + node = stream->first_node; + } + else{ + node = node->next; + } + if (node != 0){ + chunk_out->size = node->size; + chunk_out->str = node->data; + } + else{ + chunk_out->size = 0; + chunk_out->str = 0; + } + return((STREAM_Handle*)node); +} + +// stream helpers + +MR4TH_SYMBOL String8 +stream_read(Arena *arena, STREAM *stream){ + String8 result = {0}; + result.str = push_array(arena, U8, stream->total_size); + result.size = stream->total_size; + + U64 pos = 0; + for (STREAM_Node *node = stream->first_node; + node != 0; + node = node->next){ + MemoryCopy(result.str + pos, node->data, node->size); + pos += node->size; + } + return(result); +} + +MR4TH_SYMBOL void +stream_printfv(STREAM *stream, char *fmt, va_list args){ + // in case we need to try a second time + va_list args2; + va_copy(args2, args); + + // try to get a buffer from the stream + STREAM_Node *node = 0; + U8 *buffer = 0; + U64 buffer_size = 0; + if (stream->buffer_cap > 0){ + node = stream->last_node; + buffer = node->data + node->size; + buffer_size = stream->buffer_cap - node->size; + } + + // try to build the string in the current block + U64 actual_size = 0; + if (buffer_size > 0){ + actual_size = m4_vsnprintf((char*)buffer, buffer_size, fmt, args); + } + else{ + actual_size = m4_vsnprintf(0, 0, fmt, args); + } + + // if first try worked, increment block size + if (actual_size <= buffer_size){ + node->size += actual_size; + stream->total_size += actual_size; + } + + // if first try failed, reset and try again with correct size + else{ + U8 *new_buffer = stream_allocate(stream, actual_size + 1); + U64 final_size = m4_vsnprintf((char*)new_buffer, actual_size + 1, fmt, args2); + Assert(final_size == actual_size); + } + + // end args2 + va_end(args2); +} + +MR4TH_SYMBOL void +stream_printf(STREAM *stream, char *fmt, ...){ + va_list args; + va_start(args, fmt); + stream_printfv(stream, fmt, args); + va_end(args); +} + + +//////////////////////////////// +// Win32 Implementation: Memory Functions + +#if OS_WINDOWS + +MR4TH_SYMBOL void* +os_memory_reserve(U64 size){ + void *result = VirtualAlloc(0, size, MEM_RESERVE, PAGE_READWRITE); + return(result); +} + +MR4TH_SYMBOL B32 +os_memory_commit(void *ptr, U64 size){ + B32 result = (VirtualAlloc(ptr, size, MEM_COMMIT, PAGE_READWRITE) != 0); + return(result); +} + +MR4TH_SYMBOL void +os_memory_decommit(void *ptr, U64 size){ + VirtualFree(ptr, size, MEM_DECOMMIT); +} + +MR4TH_SYMBOL void +os_memory_release(void *ptr, U64 size){ + VirtualFree(ptr, 0, MEM_RELEASE); +} + + +//////////////////////////////// +// Linux Implementation: Memory Functions + +#elif OS_LINUX + +MR4TH_SYMBOL void* +os_memory_reserve(U64 size){ + void *result = mmap(0, size, PROT_NONE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); + if (result == MAP_FAILED){ + result = 0; + } + return(result); +} + +MR4TH_SYMBOL B32 +os_memory_commit(void *ptr, U64 size){ + mprotect(ptr, size, PROT_READ|PROT_WRITE); + return(1); +} + +MR4TH_SYMBOL void +os_memory_decommit(void *ptr, U64 size){ + madvise(ptr, size, MADV_DONTNEED); + mprotect(ptr, size, PROT_NONE); +} + +MR4TH_SYMBOL void +os_memory_release(void *ptr, U64 size){ + munmap(ptr, size); +} + + +// OS Implementation Missing +#else +# error not implemented on this OS +#endif + + + +//////////////////////////////////////////////// +//////////////////////////////////////////////// +// stb_sprintf.h STB_SPRINTF_IMPLEMENTATION // +//////////////////////////////////////////////// +//////////////////////////////////////////////// + +#define stbsp__uint32 unsigned int +#define stbsp__int32 signed int + +#ifdef _MSC_VER +#define stbsp__uint64 unsigned __int64 +#define stbsp__int64 signed __int64 +#else +#define stbsp__uint64 unsigned long long +#define stbsp__int64 signed long long +#endif +#define stbsp__uint16 unsigned short + +#ifndef stbsp__uintptr +#if defined(__ppc64__) || defined(__powerpc64__) || defined(__aarch64__) || defined(_M_X64) || defined(__x86_64__) || defined(__x86_64) || defined(__s390x__) +#define stbsp__uintptr stbsp__uint64 +#else +#define stbsp__uintptr stbsp__uint32 +#endif +#endif + +#ifndef STB_SPRINTF_MSVC_MODE // used for MSVC2013 and earlier (MSVC2015 matches GCC) +#if defined(_MSC_VER) && (_MSC_VER < 1900) +#define STB_SPRINTF_MSVC_MODE +#endif +#endif + +#ifdef STB_SPRINTF_NOUNALIGNED // define this before inclusion to force stbsp_sprintf to always use aligned accesses +#define STBSP__UNALIGNED(code) +#else +#define STBSP__UNALIGNED(code) code +#endif + +// internal float utility functions +static stbsp__int32 stbsp__real_to_str(char const **start, stbsp__uint32 *len, char *out, stbsp__int32 *decimal_pos, double value, stbsp__uint32 frac_digits); +static stbsp__int32 stbsp__real_to_parts(stbsp__int64 *bits, stbsp__int32 *expo, double value); +#define STBSP__SPECIAL 0x7000 + +static char stbsp__period = '.'; +static char stbsp__comma = ','; +static struct +{ + short temp; // force next field to be 2-byte aligned + char pair[201]; +} stbsp__digitpair = +{ + 0, + "00010203040506070809101112131415161718192021222324" + "25262728293031323334353637383940414243444546474849" + "50515253545556575859606162636465666768697071727374" + "75767778798081828384858687888990919293949596979899" +}; + +STBSP__PUBLICDEF void STB_SPRINTF_DECORATE(set_separators)(char pcomma, char pperiod) +{ + stbsp__period = pperiod; + stbsp__comma = pcomma; +} + +#define STBSP__LEFTJUST 1 +#define STBSP__LEADINGPLUS 2 +#define STBSP__LEADINGSPACE 4 +#define STBSP__LEADING_0X 8 +#define STBSP__LEADINGZERO 16 +#define STBSP__INTMAX 32 +#define STBSP__TRIPLET_COMMA 64 +#define STBSP__NEGATIVE 128 +#define STBSP__MEMORY_SIZES 256 +#define STBSP__HALFWIDTH 512 + +static void stbsp__lead_sign(stbsp__uint32 fl, char *sign) +{ + sign[0] = 0; + if (fl & STBSP__NEGATIVE) { + sign[0] = 1; + sign[1] = '-'; + } else if (fl & STBSP__LEADINGSPACE) { + sign[0] = 1; + sign[1] = ' '; + } else if (fl & STBSP__LEADINGPLUS) { + sign[0] = 1; + sign[1] = '+'; + } +} + +static STBSP__ASAN stbsp__uint32 stbsp__strlen_limited(char const *s, stbsp__uint32 limit) +{ + char const * sn = s; + + // get up to 4-byte alignment + for (;;) { + if (((stbsp__uintptr)sn & 3) == 0) + break; + + if (!limit || *sn == 0) + return (stbsp__uint32)(sn - s); + + ++sn; + --limit; + } + + // scan over 4 bytes at a time to find terminating 0 + // this will intentionally scan up to 3 bytes past the end of buffers, + // but becase it works 4B aligned, it will never cross page boundaries + // (hence the STBSP__ASAN markup; the over-read here is intentional + // and harmless) + while (limit >= 4) { + stbsp__uint32 v = *(stbsp__uint32 *)sn; + // bit hack to find if there's a 0 byte in there + if ((v - 0x01010101) & (~v) & 0x80808080UL) + break; + + sn += 4; + limit -= 4; + } + + // handle the last few characters to find actual size + while (limit && *sn) { + ++sn; + --limit; + } + + return (stbsp__uint32)(sn - s); +} + +STBSP__PUBLICDEF int STB_SPRINTF_DECORATE(vsprintfcb)(STBSP_SPRINTFCB *callback, void *user, char *buf, char const *fmt, va_list va) +{ + static char hex[] = "0123456789abcdefxp"; + static char hexu[] = "0123456789ABCDEFXP"; + static char spaces[] = + " " + " " + " " + " "; + char *bf; + char const *f; + int tlen = 0; + + bf = buf; + f = fmt; + for (;;) { + stbsp__int32 fw, pr, tz; + stbsp__uint32 fl; + + // macros for the callback buffer stuff +#define stbsp__chk_cb_bufL(bytes) \ +{ \ +int len = (int)(bf - buf); \ +if ((len + (bytes)) >= STB_SPRINTF_MIN) { \ +tlen += len; \ +if (0 == (bf = buf = callback(buf, user, len))) \ +goto done; \ +} \ +} +#define stbsp__chk_cb_buf(bytes) \ +{ \ +if (callback) { \ +stbsp__chk_cb_bufL(bytes); \ +} \ +} +#define stbsp__flush_cb() \ +{ \ +stbsp__chk_cb_bufL(STB_SPRINTF_MIN - 1); \ +} // flush if there is even one byte in the buffer +#define stbsp__cb_buf_clamp(cl, v) \ +cl = v; \ +if (callback) { \ +int lg = STB_SPRINTF_MIN - (int)(bf - buf); \ +if (cl > lg) \ +cl = lg; \ +} + + // fast copy everything up to the next % (or end of string) + for (;;) { + while (((stbsp__uintptr)f) & 3) { + schk1: + if (f[0] == '%') + goto scandd; + schk2: + if (f[0] == 0) + goto endfmt; + stbsp__chk_cb_buf(1); + *bf++ = f[0]; + ++f; + } + for (;;) { + // Check if the next 4 bytes contain %(0x25) or end of string. + // Using the 'hasless' trick: + // https://graphics.stanford.edu/~seander/bithacks.html#HasLessInWord + stbsp__uint32 v, c; + v = *(stbsp__uint32 *)f; + c = (~v) & 0x80808080; + if (((v ^ 0x25252525) - 0x01010101) & c) + goto schk1; + if ((v - 0x01010101) & c) + goto schk2; + if (callback) + if ((STB_SPRINTF_MIN - (int)(bf - buf)) < 4) + goto schk1; +#ifdef STB_SPRINTF_NOUNALIGNED + if(((stbsp__uintptr)bf) & 3) { + bf[0] = f[0]; + bf[1] = f[1]; + bf[2] = f[2]; + bf[3] = f[3]; + } else +#endif + { + *(stbsp__uint32 *)bf = v; + } + bf += 4; + f += 4; + } + } + scandd: + + ++f; + + // ok, we have a percent, read the modifiers first + fw = 0; + pr = -1; + fl = 0; + tz = 0; + + // flags + for (;;) { + switch (f[0]) { + // if we have left justify + case '-': + fl |= STBSP__LEFTJUST; + ++f; + continue; + // if we have leading plus + case '+': + fl |= STBSP__LEADINGPLUS; + ++f; + continue; + // if we have leading space + case ' ': + fl |= STBSP__LEADINGSPACE; + ++f; + continue; + // if we have leading 0x + case '#': + fl |= STBSP__LEADING_0X; + ++f; + continue; + // if we have thousand commas + case '\'': + fl |= STBSP__TRIPLET_COMMA; + ++f; + continue; + // if we have memory sizes + case '$': + fl |= STBSP__MEMORY_SIZES; + ++f; + continue; + // if we have leading zero + case '0': + fl |= STBSP__LEADINGZERO; + ++f; + goto flags_done; + default: goto flags_done; + } + } + flags_done: + + // get the field width + if (f[0] == '*') { + fw = va_arg(va, stbsp__uint32); + ++f; + } else { + while ((f[0] >= '0') && (f[0] <= '9')) { + fw = fw * 10 + f[0] - '0'; + f++; + } + } + // get the precision + if (f[0] == '.') { + ++f; + if (f[0] == '*') { + pr = va_arg(va, stbsp__uint32); + ++f; + } else { + pr = 0; + while ((f[0] >= '0') && (f[0] <= '9')) { + pr = pr * 10 + f[0] - '0'; + f++; + } + } + } + + // handle integer size overrides + switch (f[0]) { + // are we halfwidth? + case 'h': + fl |= STBSP__HALFWIDTH; + ++f; + if (f[0] == 'h') + ++f; // QUARTERWIDTH + break; + // are we 64-bit (unix style) + case 'l': + fl |= ((sizeof(long) == 8) ? STBSP__INTMAX : 0); + ++f; + if (f[0] == 'l') { + fl |= STBSP__INTMAX; + ++f; + } + break; + // are we 64-bit on intmax? (c99) + case 'j': + fl |= (sizeof(size_t) == 8) ? STBSP__INTMAX : 0; + ++f; + break; + // are we 64-bit on size_t or ptrdiff_t? (c99) + case 'z': + fl |= (sizeof(ptrdiff_t) == 8) ? STBSP__INTMAX : 0; + ++f; + break; + case 't': + fl |= (sizeof(ptrdiff_t) == 8) ? STBSP__INTMAX : 0; + ++f; + break; + // are we 64-bit (msft style) + case 'I': + if ((f[1] == '6') && (f[2] == '4')) { + fl |= STBSP__INTMAX; + f += 3; + } else if ((f[1] == '3') && (f[2] == '2')) { + f += 3; + } else { + fl |= ((sizeof(void *) == 8) ? STBSP__INTMAX : 0); + ++f; + } + break; + default: break; + } + + // handle each replacement + switch (f[0]) { +#define STBSP__NUMSZ 512 // big enough for e308 (with commas) or e-307 + char num[STBSP__NUMSZ]; + char lead[8]; + char tail[8]; + char *s; + char const *h; + stbsp__uint32 l, n, cs; + stbsp__uint64 n64; + double fv; + stbsp__int32 dp; + char const *sn; + + // NOTE(allen): MODIFICATION + // %S prints str (parameter: String8 str) + case 'S': + { + String8 str = va_arg(va, String8); + s = (char*)str.str; + l = (pr >= 0 && pr < str.size) ? pr : (U32)str.size; + lead[0] = 0; + tail[0] = 0; + pr = 0; + dp = 0; + cs = 0; + goto scopy; + } + + // NOTE(allen): MODIFICATION + // %N prints n spaces (parameter: int n) + case 'N': + { + // TODO(allen): there's probably a better way to set this + // up so that it doesn't rely on the buffer of spaces - + // perhaps a way to apply the space filling in the left justify path? + l = va_arg(va, int); + l = (sizeof(spaces) - 1 < l) ? (sizeof(spaces) - 1) : l; + l = (pr >= 0 && pr < l) ? pr : l; + s = spaces; + lead[0] = 0; + tail[0] = 0; + pr = 0; + dp = 0; + cs = 0; + goto scopy; + } + + case 's': + { + // get the string + s = va_arg(va, char *); + if (s == 0) + s = (char *)"null"; + // get the length, limited to desired precision + // always limit to ~0u chars since our counts are 32b + l = stbsp__strlen_limited(s, (pr >= 0) ? pr : ~0u); + lead[0] = 0; + tail[0] = 0; + pr = 0; + dp = 0; + cs = 0; + // copy the string in + goto scopy; + } + + case 'c': // char + { + // get the character + s = num + STBSP__NUMSZ - 1; + *s = (char)va_arg(va, int); + l = 1; + lead[0] = 0; + tail[0] = 0; + pr = 0; + dp = 0; + cs = 0; + goto scopy; + } + + case 'n': // weird write-bytes specifier + { + int *d = va_arg(va, int *); + *d = tlen + (int)(bf - buf); + } break; + + case 'A': // hex float + case 'a': // hex float + { + h = (f[0] == 'A') ? hexu : hex; + fv = va_arg(va, double); + if (pr == -1) + pr = 6; // default is 6 + // read the double into a string + if (stbsp__real_to_parts((stbsp__int64 *)&n64, &dp, fv)) + fl |= STBSP__NEGATIVE; + + s = num + 64; + + stbsp__lead_sign(fl, lead); + + if (dp == -1023) + dp = (n64) ? -1022 : 0; + else + n64 |= (((stbsp__uint64)1) << 52); + n64 <<= (64 - 56); + if (pr < 15) + n64 += ((((stbsp__uint64)8) << 56) >> (pr * 4)); + // add leading chars + +#ifdef STB_SPRINTF_MSVC_MODE + *s++ = '0'; + *s++ = 'x'; +#else + lead[1 + lead[0]] = '0'; + lead[2 + lead[0]] = 'x'; + lead[0] += 2; +#endif + *s++ = h[(n64 >> 60) & 15]; + n64 <<= 4; + if (pr) + *s++ = stbsp__period; + sn = s; + + // print the bits + n = pr; + if (n > 13) + n = 13; + if (pr > (stbsp__int32)n) + tz = pr - n; + pr = 0; + while (n--) { + *s++ = h[(n64 >> 60) & 15]; + n64 <<= 4; + } + + // print the expo + tail[1] = h[17]; + if (dp < 0) { + tail[2] = '-'; + dp = -dp; + } else + tail[2] = '+'; + n = (dp >= 1000) ? 6 : ((dp >= 100) ? 5 : ((dp >= 10) ? 4 : 3)); + tail[0] = (char)n; + for (;;) { + tail[n] = '0' + dp % 10; + if (n <= 3) + break; + --n; + dp /= 10; + } + + dp = (int)(s - sn); + l = (int)(s - (num + 64)); + s = num + 64; + cs = 1 + (3 << 24); + goto scopy; + } + + case 'G': // float + case 'g': // float + { + h = (f[0] == 'G') ? hexu : hex; + fv = va_arg(va, double); + if (pr == -1) + pr = 6; + else if (pr == 0) + pr = 1; // default is 6 + // read the double into a string + if (stbsp__real_to_str(&sn, &l, num, &dp, fv, (pr - 1) | 0x80000000)) + fl |= STBSP__NEGATIVE; + + // clamp the precision and delete extra zeros after clamp + n = pr; + if (l > (stbsp__uint32)pr) + l = pr; + while ((l > 1) && (pr) && (sn[l - 1] == '0')) { + --pr; + --l; + } + + // should we use %e + if ((dp <= -4) || (dp > (stbsp__int32)n)) { + if (pr > (stbsp__int32)l) + pr = l - 1; + else if (pr) + --pr; // when using %e, there is one digit before the decimal + goto doexpfromg; + } + // this is the insane action to get the pr to match %g semantics for %f + if (dp > 0) { + pr = (dp < (stbsp__int32)l) ? l - dp : 0; + } else { + pr = -dp + ((pr > (stbsp__int32)l) ? (stbsp__int32) l : pr); + } + goto dofloatfromg; + } + + case 'E': // float + case 'e': // float + { + h = (f[0] == 'E') ? hexu : hex; + fv = va_arg(va, double); + if (pr == -1) + pr = 6; // default is 6 + // read the double into a string + if (stbsp__real_to_str(&sn, &l, num, &dp, fv, pr | 0x80000000)) + fl |= STBSP__NEGATIVE; + goto doexpfromg; + } + + doexpfromg: + { + tail[0] = 0; + stbsp__lead_sign(fl, lead); + if (dp == STBSP__SPECIAL) { + s = (char *)sn; + cs = 0; + pr = 0; + goto scopy; + } + s = num + 64; + // handle leading chars + *s++ = sn[0]; + + if (pr) + *s++ = stbsp__period; + + // handle after decimal + if ((l - 1) > (stbsp__uint32)pr) + l = pr + 1; + for (n = 1; n < l; n++) + *s++ = sn[n]; + // trailing zeros + tz = pr - (l - 1); + pr = 0; + // dump expo + tail[1] = h[0xe]; + dp -= 1; + if (dp < 0) { + tail[2] = '-'; + dp = -dp; + } else + tail[2] = '+'; +#ifdef STB_SPRINTF_MSVC_MODE + n = 5; +#else + n = (dp >= 100) ? 5 : 4; +#endif + tail[0] = (char)n; + for (;;) { + tail[n] = '0' + dp % 10; + if (n <= 3) + break; + --n; + dp /= 10; + } + cs = 1 + (3 << 24); // how many tens + goto flt_lead; + } + + case 'f': // float + { + fv = va_arg(va, double); + goto doafloat; + } + + doafloat: + { + // do kilos + if (fl & STBSP__MEMORY_SIZES) { + double divisor = 1024.f; + while (fl < 0x4000000) { + if ((fv < divisor) && (fv > -divisor)) + break; + fv /= divisor; + fl += 0x1000000; + } + } + if (pr == -1) + pr = 6; // default is 6 + // read the double into a string + if (stbsp__real_to_str(&sn, &l, num, &dp, fv, pr)) + fl |= STBSP__NEGATIVE; + } + + dofloatfromg: + { + tail[0] = 0; + stbsp__lead_sign(fl, lead); + if (dp == STBSP__SPECIAL) { + s = (char *)sn; + cs = 0; + pr = 0; + goto scopy; + } + s = num + 64; + + // handle the three decimal varieties + if (dp <= 0) { + stbsp__int32 i; + // handle 0.000*000xxxx + *s++ = '0'; + if (pr) + *s++ = stbsp__period; + n = -dp; + if ((stbsp__int32)n > pr) + n = pr; + i = n; + while (i) { + if ((((stbsp__uintptr)s) & 3) == 0) + break; + *s++ = '0'; + --i; + } + while (i >= 4) { + *(stbsp__uint32 *)s = 0x30303030; + s += 4; + i -= 4; + } + while (i) { + *s++ = '0'; + --i; + } + if ((stbsp__int32)(l + n) > pr) + l = pr - n; + i = l; + while (i) { + *s++ = *sn++; + --i; + } + tz = pr - (n + l); + cs = 1 + (3 << 24); // how many tens did we write (for commas below) + } else { + cs = (fl & STBSP__TRIPLET_COMMA) ? ((600 - (stbsp__uint32)dp) % 3) : 0; + if ((stbsp__uint32)dp >= l) { + // handle xxxx000*000.0 + n = 0; + for (;;) { + if ((fl & STBSP__TRIPLET_COMMA) && (++cs == 4)) { + cs = 0; + *s++ = stbsp__comma; + } else { + *s++ = sn[n]; + ++n; + if (n >= l) + break; + } + } + if (n < (stbsp__uint32)dp) { + n = dp - n; + if ((fl & STBSP__TRIPLET_COMMA) == 0) { + while (n) { + if ((((stbsp__uintptr)s) & 3) == 0) + break; + *s++ = '0'; + --n; + } + while (n >= 4) { + *(stbsp__uint32 *)s = 0x30303030; + s += 4; + n -= 4; + } + } + while (n) { + if ((fl & STBSP__TRIPLET_COMMA) && (++cs == 4)) { + cs = 0; + *s++ = stbsp__comma; + } else { + *s++ = '0'; + --n; + } + } + } + cs = (int)(s - (num + 64)) + (3 << 24); // cs is how many tens + if (pr) { + *s++ = stbsp__period; + tz = pr; + } + } else { + // handle xxxxx.xxxx000*000 + n = 0; + for (;;) { + if ((fl & STBSP__TRIPLET_COMMA) && (++cs == 4)) { + cs = 0; + *s++ = stbsp__comma; + } else { + *s++ = sn[n]; + ++n; + if (n >= (stbsp__uint32)dp) + break; + } + } + cs = (int)(s - (num + 64)) + (3 << 24); // cs is how many tens + if (pr) + *s++ = stbsp__period; + if ((l - dp) > (stbsp__uint32)pr) + l = pr + dp; + while (n < l) { + *s++ = sn[n]; + ++n; + } + tz = pr - (l - dp); + } + } + pr = 0; + + // handle k,m,g,t + if (fl & STBSP__MEMORY_SIZES) { + tail[0] = 0; + { + char idx = 1; + tail[idx] = ' '; + idx++; + tail[idx] = " KMGT"[fl >> 24]; + idx++; + tail[idx] = 'b'; + tail[0] = idx; + } + } + goto flt_lead; + } + + flt_lead: + { + // get the length that we copied + l = (stbsp__uint32)(s - (num + 64)); + s = num + 64; + goto scopy; + } + + case 'B': // upper binary + case 'b': // lower binary + { + h = (f[0] == 'B') ? hexu : hex; + lead[0] = 0; + if (fl & STBSP__LEADING_0X) { + lead[0] = 2; + lead[1] = '0'; + lead[2] = h[0xb]; + } + l = (8 << 4) | (1 << 8); + goto radixnum; + } + + case 'o': // octal + { + h = hexu; + lead[0] = 0; + if (fl & STBSP__LEADING_0X) { + lead[0] = 1; + lead[1] = '0'; + } + l = (3 << 4) | (3 << 8); + goto radixnum; + } + + case 'p': // pointer + { + fl |= (sizeof(void *) == 8) ? STBSP__INTMAX : 0; + pr = sizeof(void *) * 2; + fl &= ~STBSP__LEADINGZERO; // 'p' only prints the pointer with zeros + // fall through - to X + } + + case 'X': // upper hex + case 'x': // lower hex + { + h = (f[0] == 'X') ? hexu : hex; + l = (4 << 4) | (4 << 8); + lead[0] = 0; + if (fl & STBSP__LEADING_0X) { + lead[0] = 2; + lead[1] = '0'; + lead[2] = h[16]; + } + goto radixnum; + } + + radixnum: + { + // get the number + if (fl & STBSP__INTMAX) + n64 = va_arg(va, stbsp__uint64); + else + n64 = va_arg(va, stbsp__uint32); + + s = num + STBSP__NUMSZ; + dp = 0; + // clear tail, and clear leading if value is zero + tail[0] = 0; + if (n64 == 0) { + lead[0] = 0; + if (pr == 0) { + l = 0; + cs = 0; + goto scopy; + } + } + // convert to string + for (;;) { + *--s = h[n64 & ((1 << (l >> 8)) - 1)]; + n64 >>= (l >> 8); + if (!((n64) || ((stbsp__int32)((num + STBSP__NUMSZ) - s) < pr))) + break; + if (fl & STBSP__TRIPLET_COMMA) { + ++l; + if ((l & 15) == ((l >> 4) & 15)) { + l &= ~15; + *--s = stbsp__comma; + } + } + }; + // get the tens and the comma pos + cs = (stbsp__uint32)((num + STBSP__NUMSZ) - s) + ((((l >> 4) & 15)) << 24); + // get the length that we copied + l = (stbsp__uint32)((num + STBSP__NUMSZ) - s); + // copy it + goto scopy; + } + + case 'u': // unsigned + case 'i': + case 'd': // integer + { + // get the integer and abs it + if (fl & STBSP__INTMAX) { + stbsp__int64 i64 = va_arg(va, stbsp__int64); + n64 = (stbsp__uint64)i64; + if ((f[0] != 'u') && (i64 < 0)) { + n64 = (stbsp__uint64)-i64; + fl |= STBSP__NEGATIVE; + } + } else { + stbsp__int32 i = va_arg(va, stbsp__int32); + n64 = (stbsp__uint32)i; + if ((f[0] != 'u') && (i < 0)) { + n64 = (stbsp__uint32)-i; + fl |= STBSP__NEGATIVE; + } + } + + if (fl & STBSP__MEMORY_SIZES) { + if (n64 < 1024) + pr = 0; + else if (pr == -1) + pr = 1; + fv = (double)(stbsp__int64)n64; + goto doafloat; + } + + // convert to string + s = num + STBSP__NUMSZ; + l = 0; + + for (;;) { + // do in 32-bit chunks (avoid lots of 64-bit divides even with constant denominators) + char *o = s - 8; + if (n64 >= 100000000) { + n = (stbsp__uint32)(n64 % 100000000); + n64 /= 100000000; + } else { + n = (stbsp__uint32)n64; + n64 = 0; + } + if ((fl & STBSP__TRIPLET_COMMA) == 0) { + do { + s -= 2; + *(stbsp__uint16 *)s = *(stbsp__uint16 *)&stbsp__digitpair.pair[(n % 100) * 2]; + n /= 100; + } while (n); + } + while (n) { + if ((fl & STBSP__TRIPLET_COMMA) && (l++ == 3)) { + l = 0; + *--s = stbsp__comma; + --o; + } else { + *--s = (char)(n % 10) + '0'; + n /= 10; + } + } + if (n64 == 0) { + if ((s[0] == '0') && (s != (num + STBSP__NUMSZ))) + ++s; + break; + } + while (s != o) + if ((fl & STBSP__TRIPLET_COMMA) && (l++ == 3)) { + l = 0; + *--s = stbsp__comma; + --o; + } else { + *--s = '0'; + } + } + + tail[0] = 0; + stbsp__lead_sign(fl, lead); + + // get the length that we copied + l = (stbsp__uint32)((num + STBSP__NUMSZ) - s); + if (l == 0) { + *--s = '0'; + l = 1; + } + cs = l + (3 << 24); + if (pr < 0) + pr = 0; + goto scopy; + } + + default: // unknown, just copy code + { + s = num + STBSP__NUMSZ - 1; + *s = f[0]; + l = 1; + fw = fl = 0; + lead[0] = 0; + tail[0] = 0; + pr = 0; + dp = 0; + cs = 0; + goto scopy; + } + + scopy: + // get fw=leading/trailing space, pr=leading zeros + if (pr < (stbsp__int32)l) + pr = l; + n = pr + lead[0] + tail[0] + tz; + if (fw < (stbsp__int32)n) + fw = n; + fw -= n; + pr -= l; + + // handle right justify and leading zeros + if ((fl & STBSP__LEFTJUST) == 0) { + if (fl & STBSP__LEADINGZERO) // if leading zeros, everything is in pr + { + pr = (fw > pr) ? fw : pr; + fw = 0; + } else { + fl &= ~STBSP__TRIPLET_COMMA; // if no leading zeros, then no commas + } + } + + // copy the spaces and/or zeros + if (fw + pr) { + stbsp__int32 i; + stbsp__uint32 c; + + // copy leading spaces (or when doing %8.4d stuff) + if ((fl & STBSP__LEFTJUST) == 0) + while (fw > 0) { + stbsp__cb_buf_clamp(i, fw); + fw -= i; + while (i) { + if ((((stbsp__uintptr)bf) & 3) == 0) + break; + *bf++ = ' '; + --i; + } + while (i >= 4) { + *(stbsp__uint32 *)bf = 0x20202020; + bf += 4; + i -= 4; + } + while (i) { + *bf++ = ' '; + --i; + } + stbsp__chk_cb_buf(1); + } + + // copy leader + sn = lead + 1; + while (lead[0]) { + stbsp__cb_buf_clamp(i, lead[0]); + lead[0] -= (char)i; + while (i) { + *bf++ = *sn++; + --i; + } + stbsp__chk_cb_buf(1); + } + + // copy leading zeros + c = cs >> 24; + cs &= 0xffffff; + cs = (fl & STBSP__TRIPLET_COMMA) ? ((stbsp__uint32)(c - ((pr + cs) % (c + 1)))) : 0; + while (pr > 0) { + stbsp__cb_buf_clamp(i, pr); + pr -= i; + if ((fl & STBSP__TRIPLET_COMMA) == 0) { + while (i) { + if ((((stbsp__uintptr)bf) & 3) == 0) + break; + *bf++ = '0'; + --i; + } + while (i >= 4) { + *(stbsp__uint32 *)bf = 0x30303030; + bf += 4; + i -= 4; + } + } + while (i) { + if ((fl & STBSP__TRIPLET_COMMA) && (cs++ == c)) { + cs = 0; + *bf++ = stbsp__comma; + } else + *bf++ = '0'; + --i; + } + stbsp__chk_cb_buf(1); + } + } + + // copy leader if there is still one + sn = lead + 1; + while (lead[0]) { + stbsp__int32 i; + stbsp__cb_buf_clamp(i, lead[0]); + lead[0] -= (char)i; + while (i) { + *bf++ = *sn++; + --i; + } + stbsp__chk_cb_buf(1); + } + + // copy the string + n = l; + while (n) { + stbsp__int32 i; + stbsp__cb_buf_clamp(i, n); + n -= i; + STBSP__UNALIGNED(while (i >= 4) { + *(stbsp__uint32 volatile *)bf = *(stbsp__uint32 volatile *)s; + bf += 4; + s += 4; + i -= 4; + }) + while (i) { + *bf++ = *s++; + --i; + } + stbsp__chk_cb_buf(1); + } + + // copy trailing zeros + while (tz) { + stbsp__int32 i; + stbsp__cb_buf_clamp(i, tz); + tz -= i; + while (i) { + if ((((stbsp__uintptr)bf) & 3) == 0) + break; + *bf++ = '0'; + --i; + } + while (i >= 4) { + *(stbsp__uint32 *)bf = 0x30303030; + bf += 4; + i -= 4; + } + while (i) { + *bf++ = '0'; + --i; + } + stbsp__chk_cb_buf(1); + } + + // copy tail if there is one + sn = tail + 1; + while (tail[0]) { + stbsp__int32 i; + stbsp__cb_buf_clamp(i, tail[0]); + tail[0] -= (char)i; + while (i) { + *bf++ = *sn++; + --i; + } + stbsp__chk_cb_buf(1); + } + + // handle the left justify + if (fl & STBSP__LEFTJUST) + if (fw > 0) { + while (fw) { + stbsp__int32 i; + stbsp__cb_buf_clamp(i, fw); + fw -= i; + while (i) { + if ((((stbsp__uintptr)bf) & 3) == 0) + break; + *bf++ = ' '; + --i; + } + while (i >= 4) { + *(stbsp__uint32 *)bf = 0x20202020; + bf += 4; + i -= 4; + } + while (i--) + *bf++ = ' '; + stbsp__chk_cb_buf(1); + } + } + break; + } + ++f; + } + endfmt: + + if (!callback) + *bf = 0; + else + stbsp__flush_cb(); + + done: + return tlen + (int)(bf - buf); +} + +// cleanup +#undef STBSP__LEFTJUST +#undef STBSP__LEADINGPLUS +#undef STBSP__LEADINGSPACE +#undef STBSP__LEADING_0X +#undef STBSP__LEADINGZERO +#undef STBSP__INTMAX +#undef STBSP__TRIPLET_COMMA +#undef STBSP__NEGATIVE +#undef STBSP__METRIC_SUFFIX +#undef STBSP__NUMSZ +#undef stbsp__chk_cb_bufL +#undef stbsp__chk_cb_buf +#undef stbsp__flush_cb +#undef stbsp__cb_buf_clamp + +// ============================================================================ +// wrapper functions + +STBSP__PUBLICDEF int STB_SPRINTF_DECORATE(sprintf)(char *buf, char const *fmt, ...) +{ + int result; + va_list va; + va_start(va, fmt); + result = STB_SPRINTF_DECORATE(vsprintfcb)(0, 0, buf, fmt, va); + va_end(va); + return result; +} + +typedef struct stbsp__context { + char *buf; + int count; + int length; + char tmp[STB_SPRINTF_MIN]; +} stbsp__context; + +static char *stbsp__clamp_callback(const char *buf, void *user, int len) +{ + stbsp__context *c = (stbsp__context *)user; + c->length += len; + + if (len > c->count) + len = c->count; + + if (len) { + if (buf != c->buf) { + const char *s, *se; + char *d; + d = c->buf; + s = buf; + se = buf + len; + do { + *d++ = *s++; + } while (s < se); + } + c->buf += len; + c->count -= len; + } + + if (c->count <= 0) + return c->tmp; + return (c->count >= STB_SPRINTF_MIN) ? c->buf : c->tmp; // go direct into buffer if you can +} + +static char * stbsp__count_clamp_callback( const char * buf, void * user, int len ) +{ + stbsp__context * c = (stbsp__context*)user; + (void) sizeof(buf); + + c->length += len; + return c->tmp; // go direct into buffer if you can +} + +STBSP__PUBLICDEF int STB_SPRINTF_DECORATE( vsnprintf )( char * buf, int count, char const * fmt, va_list va ) +{ + stbsp__context c; + + if ( (count == 0) && !buf ) + { + c.length = 0; + + STB_SPRINTF_DECORATE( vsprintfcb )( stbsp__count_clamp_callback, &c, c.tmp, fmt, va ); + } + else + { + int l; + + c.buf = buf; + c.count = count; + c.length = 0; + + STB_SPRINTF_DECORATE( vsprintfcb )( stbsp__clamp_callback, &c, stbsp__clamp_callback(0,&c,0), fmt, va ); + + // zero-terminate + l = (int)( c.buf - buf ); + if ( l >= count ) // should never be greater, only equal (or less) than count + l = count - 1; + buf[l] = 0; + } + + return c.length; +} + +STBSP__PUBLICDEF int STB_SPRINTF_DECORATE(snprintf)(char *buf, int count, char const *fmt, ...) +{ + int result; + va_list va; + va_start(va, fmt); + + result = STB_SPRINTF_DECORATE(vsnprintf)(buf, count, fmt, va); + va_end(va); + + return result; +} + +STBSP__PUBLICDEF int STB_SPRINTF_DECORATE(vsprintf)(char *buf, char const *fmt, va_list va) +{ + return STB_SPRINTF_DECORATE(vsprintfcb)(0, 0, buf, fmt, va); +} + +// ======================================================================= +// low level float utility functions + +// copies d to bits w/ strict aliasing (this compiles to nothing on /Ox) +#define STBSP__COPYFP(dest, src) \ +{ \ +int cn; \ +for (cn = 0; cn < 8; cn++) \ +((char *)&dest)[cn] = ((char *)&src)[cn]; \ +} + +// get float info +static stbsp__int32 stbsp__real_to_parts(stbsp__int64 *bits, stbsp__int32 *expo, double value) +{ + double d; + stbsp__int64 b = 0; + + // load value and round at the frac_digits + d = value; + + STBSP__COPYFP(b, d); + + *bits = b & ((((stbsp__uint64)1) << 52) - 1); + *expo = (stbsp__int32)(((b >> 52) & 2047) - 1023); + + return (stbsp__int32)((stbsp__uint64) b >> 63); +} + +static double const stbsp__bot[23] = { + 1e+000, 1e+001, 1e+002, 1e+003, 1e+004, 1e+005, 1e+006, 1e+007, 1e+008, 1e+009, 1e+010, 1e+011, + 1e+012, 1e+013, 1e+014, 1e+015, 1e+016, 1e+017, 1e+018, 1e+019, 1e+020, 1e+021, 1e+022 +}; +static double const stbsp__negbot[22] = { + 1e-001, 1e-002, 1e-003, 1e-004, 1e-005, 1e-006, 1e-007, 1e-008, 1e-009, 1e-010, 1e-011, + 1e-012, 1e-013, 1e-014, 1e-015, 1e-016, 1e-017, 1e-018, 1e-019, 1e-020, 1e-021, 1e-022 +}; +static double const stbsp__negboterr[22] = { + -5.551115123125783e-018, -2.0816681711721684e-019, -2.0816681711721686e-020, -4.7921736023859299e-021, -8.1803053914031305e-022, 4.5251888174113741e-023, + 4.5251888174113739e-024, -2.0922560830128471e-025, -6.2281591457779853e-026, -3.6432197315497743e-027, 6.0503030718060191e-028, 2.0113352370744385e-029, + -3.0373745563400371e-030, 1.1806906454401013e-032, -7.7705399876661076e-032, 2.0902213275965398e-033, -7.1542424054621921e-034, -7.1542424054621926e-035, + 2.4754073164739869e-036, 5.4846728545790429e-037, 9.2462547772103625e-038, -4.8596774326570872e-039 +}; +static double const stbsp__top[13] = { + 1e+023, 1e+046, 1e+069, 1e+092, 1e+115, 1e+138, 1e+161, 1e+184, 1e+207, 1e+230, 1e+253, 1e+276, 1e+299 +}; +static double const stbsp__negtop[13] = { + 1e-023, 1e-046, 1e-069, 1e-092, 1e-115, 1e-138, 1e-161, 1e-184, 1e-207, 1e-230, 1e-253, 1e-276, 1e-299 +}; +static double const stbsp__toperr[13] = { + 8388608, + 6.8601809640529717e+028, + -7.253143638152921e+052, + -4.3377296974619174e+075, + -1.5559416129466825e+098, + -3.2841562489204913e+121, + -3.7745893248228135e+144, + -1.7356668416969134e+167, + -3.8893577551088374e+190, + -9.9566444326005119e+213, + 6.3641293062232429e+236, + -5.2069140800249813e+259, + -5.2504760255204387e+282 +}; +static double const stbsp__negtoperr[13] = { + 3.9565301985100693e-040, -2.299904345391321e-063, 3.6506201437945798e-086, 1.1875228833981544e-109, + -5.0644902316928607e-132, -6.7156837247865426e-155, -2.812077463003139e-178, -5.7778912386589953e-201, + 7.4997100559334532e-224, -4.6439668915134491e-247, -6.3691100762962136e-270, -9.436808465446358e-293, + 8.0970921678014997e-317 +}; + +#if defined(_MSC_VER) && (_MSC_VER <= 1200) +static stbsp__uint64 const stbsp__powten[20] = { + 1, + 10, + 100, + 1000, + 10000, + 100000, + 1000000, + 10000000, + 100000000, + 1000000000, + 10000000000, + 100000000000, + 1000000000000, + 10000000000000, + 100000000000000, + 1000000000000000, + 10000000000000000, + 100000000000000000, + 1000000000000000000, + 10000000000000000000U +}; +#define stbsp__tento19th ((stbsp__uint64)1000000000000000000) +#else +static stbsp__uint64 const stbsp__powten[20] = { + 1, + 10, + 100, + 1000, + 10000, + 100000, + 1000000, + 10000000, + 100000000, + 1000000000, + 10000000000ULL, + 100000000000ULL, + 1000000000000ULL, + 10000000000000ULL, + 100000000000000ULL, + 1000000000000000ULL, + 10000000000000000ULL, + 100000000000000000ULL, + 1000000000000000000ULL, + 10000000000000000000ULL +}; +#define stbsp__tento19th (1000000000000000000ULL) +#endif + +#define stbsp__ddmulthi(oh, ol, xh, yh) \ +{ \ +double ahi = 0, alo, bhi = 0, blo; \ +stbsp__int64 bt; \ +oh = xh * yh; \ +STBSP__COPYFP(bt, xh); \ +bt &= ((~(stbsp__uint64)0) << 27); \ +STBSP__COPYFP(ahi, bt); \ +alo = xh - ahi; \ +STBSP__COPYFP(bt, yh); \ +bt &= ((~(stbsp__uint64)0) << 27); \ +STBSP__COPYFP(bhi, bt); \ +blo = yh - bhi; \ +ol = ((ahi * bhi - oh) + ahi * blo + alo * bhi) + alo * blo; \ +} + +#define stbsp__ddtoS64(ob, xh, xl) \ +{ \ +double ahi = 0, alo, vh, t; \ +ob = (stbsp__int64)xh; \ +vh = (double)ob; \ +ahi = (xh - vh); \ +t = (ahi - xh); \ +alo = (xh - (ahi - t)) - (vh + t); \ +ob += (stbsp__int64)(ahi + alo + xl); \ +} + +#define stbsp__ddrenorm(oh, ol) \ +{ \ +double s; \ +s = oh + ol; \ +ol = ol - (s - oh); \ +oh = s; \ +} + +#define stbsp__ddmultlo(oh, ol, xh, xl, yh, yl) ol = ol + (xh * yl + xl * yh); + +#define stbsp__ddmultlos(oh, ol, xh, yl) ol = ol + (xh * yl); + +static void stbsp__raise_to_power10(double *ohi, double *olo, double d, stbsp__int32 power) // power can be -323 to +350 +{ + double ph, pl; + if ((power >= 0) && (power <= 22)) { + stbsp__ddmulthi(ph, pl, d, stbsp__bot[power]); + } else { + stbsp__int32 e, et, eb; + double p2h, p2l; + + e = power; + if (power < 0) + e = -e; + et = (e * 0x2c9) >> 14; /* %23 */ + if (et > 13) + et = 13; + eb = e - (et * 23); + + ph = d; + pl = 0.0; + if (power < 0) { + if (eb) { + --eb; + stbsp__ddmulthi(ph, pl, d, stbsp__negbot[eb]); + stbsp__ddmultlos(ph, pl, d, stbsp__negboterr[eb]); + } + if (et) { + stbsp__ddrenorm(ph, pl); + --et; + stbsp__ddmulthi(p2h, p2l, ph, stbsp__negtop[et]); + stbsp__ddmultlo(p2h, p2l, ph, pl, stbsp__negtop[et], stbsp__negtoperr[et]); + ph = p2h; + pl = p2l; + } + } else { + if (eb) { + e = eb; + if (eb > 22) + eb = 22; + e -= eb; + stbsp__ddmulthi(ph, pl, d, stbsp__bot[eb]); + if (e) { + stbsp__ddrenorm(ph, pl); + stbsp__ddmulthi(p2h, p2l, ph, stbsp__bot[e]); + stbsp__ddmultlos(p2h, p2l, stbsp__bot[e], pl); + ph = p2h; + pl = p2l; + } + } + if (et) { + stbsp__ddrenorm(ph, pl); + --et; + stbsp__ddmulthi(p2h, p2l, ph, stbsp__top[et]); + stbsp__ddmultlo(p2h, p2l, ph, pl, stbsp__top[et], stbsp__toperr[et]); + ph = p2h; + pl = p2l; + } + } + } + stbsp__ddrenorm(ph, pl); + *ohi = ph; + *olo = pl; +} + +// given a float value, returns the significant bits in bits, and the position of the +// decimal point in decimal_pos. +/-INF and NAN are specified by special values +// returned in the decimal_pos parameter. +// frac_digits is absolute normally, but if you want from first significant digits (got %g and %e), or in 0x80000000 +static stbsp__int32 stbsp__real_to_str(char const **start, stbsp__uint32 *len, char *out, stbsp__int32 *decimal_pos, double value, stbsp__uint32 frac_digits) +{ + double d; + stbsp__int64 bits = 0; + stbsp__int32 expo, e, ng, tens; + + d = value; + STBSP__COPYFP(bits, d); + expo = (stbsp__int32)((bits >> 52) & 2047); + ng = (stbsp__int32)((stbsp__uint64) bits >> 63); + if (ng) + d = -d; + + if (expo == 2047) // is nan or inf? + { + *start = (bits & ((((stbsp__uint64)1) << 52) - 1)) ? "NaN" : "Inf"; + *decimal_pos = STBSP__SPECIAL; + *len = 3; + return ng; + } + + if (expo == 0) // is zero or denormal + { + if (((stbsp__uint64) bits << 1) == 0) // do zero + { + *decimal_pos = 1; + *start = out; + out[0] = '0'; + *len = 1; + return ng; + } + // find the right expo for denormals + { + stbsp__int64 v = ((stbsp__uint64)1) << 51; + while ((bits & v) == 0) { + --expo; + v >>= 1; + } + } + } + + // find the decimal exponent as well as the decimal bits of the value + { + double ph, pl; + + // log10 estimate - very specifically tweaked to hit or undershoot by no more than 1 of log10 of all expos 1..2046 + tens = expo - 1023; + tens = (tens < 0) ? ((tens * 617) / 2048) : (((tens * 1233) / 4096) + 1); + + // move the significant bits into position and stick them into an int + stbsp__raise_to_power10(&ph, &pl, d, 18 - tens); + + // get full as much precision from double-double as possible + stbsp__ddtoS64(bits, ph, pl); + + // check if we undershot + if (((stbsp__uint64)bits) >= stbsp__tento19th) + ++tens; + } + + // now do the rounding in integer land + frac_digits = (frac_digits & 0x80000000) ? ((frac_digits & 0x7ffffff) + 1) : (tens + frac_digits); + if ((frac_digits < 24)) { + stbsp__uint32 dg = 1; + if ((stbsp__uint64)bits >= stbsp__powten[9]) + dg = 10; + while ((stbsp__uint64)bits >= stbsp__powten[dg]) { + ++dg; + if (dg == 20) + goto noround; + } + if (frac_digits < dg) { + stbsp__uint64 r; + // add 0.5 at the right position and round + e = dg - frac_digits; + if ((stbsp__uint32)e >= 24) + goto noround; + r = stbsp__powten[e]; + bits = bits + (r / 2); + if ((stbsp__uint64)bits >= stbsp__powten[dg]) + ++tens; + bits /= r; + } + noround:; + } + + // kill long trailing runs of zeros + if (bits) { + stbsp__uint32 n; + for (;;) { + if (bits <= 0xffffffff) + break; + if (bits % 1000) + goto donez; + bits /= 1000; + } + n = (stbsp__uint32)bits; + while ((n % 1000) == 0) + n /= 1000; + bits = n; + donez:; + } + + // convert to string + out += 64; + e = 0; + for (;;) { + stbsp__uint32 n; + char *o = out - 8; + // do the conversion in chunks of U32s (avoid most 64-bit divides, worth it, constant denomiators be damned) + if (bits >= 100000000) { + n = (stbsp__uint32)(bits % 100000000); + bits /= 100000000; + } else { + n = (stbsp__uint32)bits; + bits = 0; + } + while (n) { + out -= 2; + *(stbsp__uint16 *)out = *(stbsp__uint16 *)&stbsp__digitpair.pair[(n % 100) * 2]; + n /= 100; + e += 2; + } + if (bits == 0) { + if ((e) && (out[0] == '0')) { + ++out; + --e; + } + break; + } + while (out != o) { + *--out = '0'; + ++e; + } + } + + *decimal_pos = tens; + *start = out; + *len = e; + return ng; +} + +#undef stbsp__ddmulthi +#undef stbsp__ddrenorm +#undef stbsp__ddmultlo +#undef stbsp__ddmultlos +#undef STBSP__SPECIAL +#undef STBSP__COPYFP + +// clean up +#undef stbsp__uint16 +#undef stbsp__uint32 +#undef stbsp__int32 +#undef stbsp__uint64 +#undef stbsp__int64 +#undef STBSP__UNALIGNED diff --git a/base.h b/base.h new file mode 100644 index 0000000..b67ae26 --- /dev/null +++ b/base.h @@ -0,0 +1,634 @@ +#ifndef BASE_H +#define BASE_H + +#if !defined(MR4TH_SYMBOL) +# define MR4TH_SYMBOL static +#endif + +// untangle compiler, os, & architecture +#if defined(__clang__) +# define COMPILER_CLANG 1 + +# if defined(_WIN32) +# define OS_WINDOWS 1 +# elif defined(__gnu_linux__) +# define OS_LINUX 1 +# elif defined(__APPLE__) && defined(__MACH__) +# define OS_MAC 1 +# else +# error missing OS detection +# endif + +# if defined(__amd64__) +# define ARCH_X64 1 +// TODO(allen): verify this works on clang +# elif defined(__i386__) +# define ARCH_X86 1 +// TODO(allen): verify this works on clang +# elif defined(__arm__) +# define ARCH_ARM 1 +// TODO(allen): verify this works on clang +# elif defined(__aarch64__) +# define ARCH_ARM64 1 +# else +# error missing ARCH detection +# endif + +#elif defined(_MSC_VER) +# define COMPILER_CL 1 + +# if defined(_WIN32) +# define OS_WINDOWS 1 +# else +# error missing OS detection +# endif + +# if defined(_M_AMD64) +# define ARCH_X64 1 +# elif defined(_M_I86) +# define ARCH_X86 1 +# elif defined(_M_ARM) +# define ARCH_ARM 1 +// TODO(allen): ARM64? +# else +# error missing ARCH detection +# endif + +#elif defined(__GNUC__) +# define COMPILER_GCC 1 + +# if defined(_WIN32) +# define OS_WINDOWS 1 +# elif defined(__gnu_linux__) +# define OS_LINUX 1 +# elif defined(__APPLE__) && defined(__MACH__) +# define OS_MAC 1 +# else +# error missing OS detection +# endif + +# if defined(__amd64__) +# define ARCH_X64 1 +# elif defined(__i386__) +# define ARCH_X86 1 +# elif defined(__arm__) +# define ARCH_ARM 1 +# elif defined(__aarch64__) +# define ARCH_ARM64 1 +# else +# error missing ARCH detection +# endif + +#else +# error no context cracking for this compiler +#endif + +#if !defined(COMPILER_CL) +# define COMPILER_CL 0 +#endif +#if !defined(COMPILER_CLANG) +# define COMPILER_CLANG 0 +#endif +#if !defined(COMPILER_GCC) +# define COMPILER_GCC 0 +#endif +#if !defined(OS_WINDOWS) +# define OS_WINDOWS 0 +#endif +#if !defined(OS_LINUX) +# define OS_LINUX 0 +#endif +#if !defined(OS_MAC) +# define OS_MAC 0 +#endif +#if !defined(ARCH_X64) +# define ARCH_X64 0 +#endif +#if !defined(ARCH_X86) +# define ARCH_X86 0 +#endif +#if !defined(ARCH_ARM) +# define ARCH_ARM 0 +#endif +#if !defined(ARCH_ARM64) +# define ARCH_ARM64 0 +#endif + +#if COMPILER_CL +# define MR4TH_THREADVAR __declspec(thread) +#elif COMPILER_CLANG || COMPILER_GCC +# define MR4TH_THREADVAR __thread +#else +# error MR4TH_THREADVAR not defined for this compiler +#endif + +// setup pointer size macro +#if ARCH_X64 || ARCH_ARM64 +# define ARCH_ADDRSIZE 64 +#else +# define ARCH_ADDRSIZE 32 +#endif + +//////////////////////////////// +// Macros: Assert + +#if !defined(AssertBreak) +# define AssertBreak() (*(volatile int*)0 = 0) +#endif + +#define Assert(c) do{ if (!(c)){ AssertBreak(); } }while(0) + +#define StaticAssert(c,l) typedef U8 Glue(l,__LINE__) [(c)?1:-1] + +//////////////////////////////// +// Macros: Memory + +#include + +#define MemoryZero(p,z) memset((p), 0, (z)) +#define MemoryZeroStruct(p) MemoryZero((p), sizeof(*(p))) +#define MemoryZeroArray(p) MemoryZero((p), sizeof(p)) +#define MemoryZeroTyped(p,c) MemoryZero((p), sizeof(*(p))*(c)) + +#define MemoryMatch(a,b,z) (memcmp((a),(b),(z)) == 0) + +#define MemoryCopy(d,s,z) memmove((d), (s), (z)) +#define MemoryCopyStruct(d,s) MemoryCopy((d),(s),Min(sizeof(*(d)),sizeof(*(s)))) +#define MemoryCopyArray(d,s) MemoryCopy((d),(s),Min(sizeof(s),sizeof(d))) +#define MemoryCopyTyped(d,s,c) MemoryCopy((d),(s),Min(sizeof(*(d)),sizeof(*(s)))*(c)) + +//////////////////////////////// +// Macros: Linked Lists + +#define DLLPushBack_NPZ(f,l,n,next,prev,nil)\ +(((f) == (nil))?\ +((f)=(l)=(n),(n)->next=(n)->prev=(nil)):\ +((n)->prev=(l),(l)->next=(n),(l)=(n),(n)->next=(nil))) + +#define DLLPushBack(f,l,n) DLLPushBack_NPZ(f,l,n,next,prev,0) +#define DLLPushFront(f,l,n) DLLPushBack_NPZ(l,f,n,prev,next,0) + +#define DLLInsert_NPZ(f,l,p,n,next,prev,nil) \ +(((p) != (l))?\ +((n)->next = (p)->next,\ +(n)->prev = (p),\ +(p)->next->prev = (n),\ +(p)->next = (n))\ +:((n)->next = (nil),\ +(n)->prev = (l),\ +(l)->next = (n),\ +(l) = (n))) + +#define DLLInsert(f,l,p,n) DLLInsert_NPZ(f,l,p,n,next,prev,0) + +#define DLLRemove_NPZ(f,l,n,next,prev,nil)\ +((f)==(n)?\ +((f)==(l)?\ +((f)=(l)=(nil)):\ +((f)=(f)->next,(f)->prev=(nil))):\ +(l)==(n)?\ +((l)=(l)->prev,(l)->next=(nil)):\ +((n)->next->prev=(n)->prev,\ +(n)->prev->next=(n)->next)) + +#define DLLRemove(f,l,n) DLLRemove_NPZ(f,l,n,next,prev,0) + +#define SLLQueuePush_NZ(f,l,n,next,nil) (((f)==(nil)?\ +(f)=(l)=(n):\ +((l)->next=(n),(l)=(n))),\ +(n)->next=(nil)) +#define SLLQueuePush(f,l,n) SLLQueuePush_NZ(f,l,n,next,0) + +#define SLLQueuePushFront_NZ(f,l,n,next,nil) ((f)==(nil)?\ +((f)=(l)=(n),(n)->next=(nil)):\ +((n)->next=(f),(f)=(n))) +#define SLLQueuePushFront(f,l,n) SLLQueuePushFront_NZ(f,l,n,next,0) + +#define SLLQueuePop_NZ(f,l,next,nil) ((f)==(l)?\ +(f)=(l)=(nil):\ +((f)=(f)->next)) +#define SLLQueuePop(f,l) SLLQueuePop_NZ(f,l,next,0) + +#define SLLStackPush_N(f,n,next) ((n)->next=(f),(f)=(n)) +#define SLLStackPush(f,n) SLLStackPush_N(f,n,next) + +#define SLLStackPop_NZ(f,next,nil) ((f)==(nil)?(nil):\ +((f)=(f)->next)) +#define SLLStackPop(f) SLLStackPop_NZ(f,next,0) + + +//////////////////////////////// +// Macros: Common Expressions + +#define ArrayCount(a) (sizeof(a)/sizeof(*(a))) + +#define IntFromPtr(p) (UAddr)(p) +#define PtrFromInt(n) (void*)((UAddr)(n)) +#define PtrDif(a,b) ((U8*)(a) - (U8*)(b)) + +#define AlignUpPow2(x,p) (((x) + (p) - 1)&~((p) - 1)) +#define AlignDownPow2(x,p) ((x)&~((p) - 1)) +#define IsPow2OrZero(x) (((x)&((x)-1)) == 0) + +#define Min(a,b) (((a)<(b))?(a):(b)) +#define Max(a,b) (((a)>(b))?(a):(b)) +#define Clamp(a,x,b) (((x)<(a))?(a):\ +((b)<(x))?(b):(x)) +#define ClampTop(a,b) Min(a,b) +#define ClampBot(a,b) Max(a,b) + +#define KB(x) ((U64)(x) << 10) +#define MB(x) ((U64)(x) << 20) +#define GB(x) ((U64)(x) << 30) +#define TB(x) ((U64)(x) << 40llu) + +//////////////////////////////// +// Types: Basic + +#include +#include + +typedef int8_t S8; +typedef int16_t S16; +typedef int32_t S32; +typedef int64_t S64; +typedef uint8_t U8; +typedef uint16_t U16; +typedef uint32_t U32; +typedef uint64_t U64; +typedef S8 B8; +typedef S16 B16; +typedef S32 B32; +typedef S64 B64; +typedef float F32; +typedef double F64; + +#if ARCH_ADDRSIZE == 32 +typedef U32 UAddr; +typedef S32 SAddr; +#elif ARCH_ADDRSIZE == 64 +typedef U64 UAddr; +typedef S64 SAddr; +#else +# error UAddr and SAddr not defined for this architecture +#endif + +typedef void VoidFunc(void); + +//////////////////////////////// +// Types: Arena + +typedef struct Arena{ + struct Arena *current; + struct Arena *prev; + U64 alignment; + B8 growing; + U8 filler[7]; + U64 base_pos; + U64 chunk_cap; + U64 chunk_pos; + U64 chunk_commit_pos; +} Arena; + +typedef struct ArenaTemp{ + Arena *arena; + U64 pos; +} ArenaTemp; + +//////////////////////////////// +// Types: String + +typedef struct String8{ + U8 *str; + U64 size; +} String8; + +//////////////////////////////// +// Types: Stream + +#include + +typedef void STREAM_Handle; + +typedef struct STREAM_Node{ + struct STREAM_Node *next; + U64 size; + U8 data[0]; +} STREAM_Node; + +#define STREAM_NODE_FROM_DATA(d) (STREAM_Node*)((U8*)(d) - sizeof(STREAM_Node)) + +typedef struct STREAM{ + Arena *arena; + U64 clear_pos; + STREAM_Node *first_node; + STREAM_Node *last_node; + U64 buffer_cap; + U64 total_size; + STREAM_Node *unused_node; +} STREAM; + +#define STREAM_ALLOC_SIZE MB(16) + + +//////////////////////////////// +// Functions: Arenas + +// arena core + +MR4TH_SYMBOL Arena* arena_alloc_reserve(U64 reserve_size, B32 growing); +MR4TH_SYMBOL Arena* arena_alloc(void); +MR4TH_SYMBOL void arena_release(Arena *arena); +MR4TH_SYMBOL void* arena_push_no_zero(Arena *arena, U64 size); +MR4TH_SYMBOL void arena_pop_to(Arena *arena, U64 pos); +MR4TH_SYMBOL U64 arena_current_pos(Arena *arena); + +MR4TH_SYMBOL void* arena_push(Arena *arena, U64 size); +MR4TH_SYMBOL void arena_align(Arena *arena, U64 pow2_align); +MR4TH_SYMBOL void arena_pop_amount(Arena *arena, U64 amount); + +#define push_array(a,T,c) (T*)arena_push((a), sizeof(T)*(c)) +#define push_array_no_zero(a,T,c) (T*)arena_push_no_zero((a), sizeof(T)*(c)) +#define push_array_copy(a,T,s,c) \ +(T*)memory_move(push_array_no_zero(a,T,c), (s), sizeof(T)*(c)) + +// arena temp + +MR4TH_SYMBOL ArenaTemp arena_begin_temp(Arena *arena); +MR4TH_SYMBOL void arena_end_temp(ArenaTemp *temp); + +// scratch + +MR4TH_SYMBOL ArenaTemp arena_get_scratch(Arena **conflict_array, U32 count); +#define arena_release_scratch(temp) arena_end_temp(temp) + +//////////////////////////////// +// Functions: Strings + +MR4TH_SYMBOL String8 str8(U8 *str, U64 size); +MR4TH_SYMBOL String8 str8_range(U8 *first, U8 *opl); +MR4TH_SYMBOL String8 str8_cstring(U8 *cstr); +MR4TH_SYMBOL String8 str8_cstring_capped(U8 *cstr, U8 *opl); + +#define str8_lit(s) str8((U8*)(s), sizeof(s) - 1) +#define str8_struct(s) str8((U8*)(s), sizeof(*(s))) +#define str8_array(s) str8((U8*)(s), sizeof(s)) +#define str8_lit_const(s) { (U8*)(s), sizeof(s) - 1 } + +MR4TH_SYMBOL U32 u32_from_str8_base10(String8 string); + +//////////////////////////////// +// Functions: Stream + +// stream core + +MR4TH_SYMBOL STREAM* stream_new(void); +MR4TH_SYMBOL void stream_release(STREAM *stream); + +MR4TH_SYMBOL void stream_clear(STREAM *stream); +MR4TH_SYMBOL void stream_write(STREAM *stream, String8 data); +MR4TH_SYMBOL U8* stream_allocate(STREAM *stream, U64 size); + +MR4TH_SYMBOL U64 stream_total_size(STREAM *stream); +MR4TH_SYMBOL STREAM_Handle* stream_next_chunk(STREAM *stream, STREAM_Handle *handle, String8 *chunk_out); + +// stream helpers + +MR4TH_SYMBOL String8 stream_read(Arena *arena, STREAM *stream); + +MR4TH_SYMBOL void stream_printfv(STREAM *stream, char *fmt, va_list args); +MR4TH_SYMBOL void stream_printf(STREAM *stream, char *fmt, ...); + +MR4TH_SYMBOL void stream_fprint(FILE *file, STREAM *stream); + + + +//////////////////////////////// +// Implementable Functions: Memory Functions + +MR4TH_SYMBOL void* os_memory_reserve(U64 size); +MR4TH_SYMBOL B32 os_memory_commit(void *ptr, U64 size); +MR4TH_SYMBOL void os_memory_decommit(void *ptr, U64 size); +MR4TH_SYMBOL void os_memory_release(void *ptr, U64 size); + + +#if OS_WINDOWS + +//////////////////////////////// +// Win32: Includes + +#include +#include +#include + + +#elif OS_LINUX + + +//////////////////////////////// +// Linux: Includes + +#include + + +// OS Missing +#else +# error not implemented on this OS +#endif + + + +//////////////////////////////////////////////// +//////////////////////////////////////////////// +/// stb_sprintf.h STB_SPRINTF_H_INCLUDE //// +//////////////////////////////////////////////// +//////////////////////////////////////////////// + +#define STB_SPRINTF_DECORATE(name) m4_##name + +/* +Single file sprintf replacement. + +Originally written by Jeff Roberts at RAD Game Tools - 2015/10/20. +Hereby placed in public domain. + +This is a full sprintf replacement that supports everything that +the C runtime sprintfs support, including float/double, 64-bit integers, +hex floats, field parameters (%*.*d stuff), length reads backs, etc. + +Why would you need this if sprintf already exists? Well, first off, +it's *much* faster (see below). It's also much smaller than the CRT +versions code-space-wise. We've also added some simple improvements +that are super handy (commas in thousands, callbacks at buffer full, +for example). Finally, the format strings for MSVC and GCC differ +for 64-bit integers (among other small things), so this lets you use +the same format strings in cross platform code. + +It uses the standard single file trick of being both the header file +and the source itself. If you just include it normally, you just get +the header file function definitions. To get the code, you include +it from a C or C++ file and define STB_SPRINTF_IMPLEMENTATION first. + +It only uses va_args macros from the C runtime to do it's work. It +does cast doubles to S64s and shifts and divides U64s, which does +drag in CRT code on most platforms. + +It compiles to roughly 8K with float support, and 4K without. +As a comparison, when using MSVC static libs, calling sprintf drags +in 16K. + +API: +==== +int stbsp_sprintf( char * buf, char const * fmt, ... ) +int stbsp_snprintf( char * buf, int count, char const * fmt, ... ) + Convert an arg list into a buffer. stbsp_snprintf always returns + a zero-terminated string (unlike regular snprintf). + +int stbsp_vsprintf( char * buf, char const * fmt, va_list va ) +int stbsp_vsnprintf( char * buf, int count, char const * fmt, va_list va ) + Convert a va_list arg list into a buffer. stbsp_vsnprintf always returns + a zero-terminated string (unlike regular snprintf). + +int stbsp_vsprintfcb( STBSP_SPRINTFCB * callback, void * user, char * buf, char const * fmt, va_list va ) + typedef char * STBSP_SPRINTFCB( char const * buf, void * user, int len ); + Convert into a buffer, calling back every STB_SPRINTF_MIN chars. + Your callback can then copy the chars out, print them or whatever. + This function is actually the workhorse for everything else. + The buffer you pass in must hold at least STB_SPRINTF_MIN characters. + // you return the next buffer to use or 0 to stop converting + +void stbsp_set_separators( char comma, char period ) + Set the comma and period characters to use. + +FLOATS/DOUBLES: +=============== +This code uses a internal float->ascii conversion method that uses +doubles with error correction (double-doubles, for ~105 bits of +precision). This conversion is round-trip perfect - that is, an atof +of the values output here will give you the bit-exact double back. + +One difference is that our insignificant digits will be different than +with MSVC or GCC (but they don't match each other either). We also +don't attempt to find the minimum length matching float (pre-MSVC15 +doesn't either). + +If you don't need float or doubles at all, define STB_SPRINTF_NOFLOAT +and you'll save 4K of code space. +NOTE(allen): MODIFICATION - I've hard coded that this copy *does* use floats + +64-BIT INTS: +============ +This library also supports 64-bit integers and you can use MSVC style or +GCC style indicators (%I64d or %lld). It supports the C99 specifiers +for size_t and ptr_diff_t (%jd %zd) as well. + +EXTRAS: +======= +Like some GCCs, for integers and floats, you can use a ' (single quote) +specifier and commas will be inserted on the thousands: "%'d" on 12345 +would print 12,345. + +For integers and floats, you can use a "$" specifier and the number +will be converted to float and then divided to get kilo, mega, giga or +tera and then printed, so "%$d" 1000 is "1.0 k", "%$.2d" 2536000 is +"2.53 M", etc. For byte values, use two $:s, like "%$$d" to turn +2536000 to "2.42 Mi". If you prefer JEDEC suffixes to SI ones, use three +$:s: "%$$$d" -> "2.42 M". To remove the space between the number and the +suffix, add "_" specifier: "%_$d" -> "2.53M". + +In addition to octal and hexadecimal conversions, you can print +integers in binary: "%b" for 256 would print 100. + +PERFORMANCE vs MSVC 2008 32-/64-bit (GCC is even slower than MSVC): +=================================================================== +"%d" across all 32-bit ints (4.8x/4.0x faster than 32-/64-bit MSVC) +"%24d" across all 32-bit ints (4.5x/4.2x faster) +"%x" across all 32-bit ints (4.5x/3.8x faster) +"%08x" across all 32-bit ints (4.3x/3.8x faster) +"%f" across e-10 to e+10 floats (7.3x/6.0x faster) +"%e" across e-10 to e+10 floats (8.1x/6.0x faster) +"%g" across e-10 to e+10 floats (10.0x/7.1x faster) +"%f" for values near e-300 (7.9x/6.5x faster) +"%f" for values near e+300 (10.0x/9.1x faster) +"%e" for values near e-300 (10.1x/7.0x faster) +"%e" for values near e+300 (9.2x/6.0x faster) +"%.320f" for values near e-300 (12.6x/11.2x faster) +"%a" for random values (8.6x/4.3x faster) +"%I64d" for 64-bits with 32-bit values (4.8x/3.4x faster) +"%I64d" for 64-bits > 32-bit values (4.9x/5.5x faster) +"%s%s%s" for 64 char strings (7.1x/7.3x faster) +"...512 char string..." ( 35.0x/32.5x faster!) +*/ + +#if defined(__clang__) +#if defined(__has_feature) && defined(__has_attribute) +#if __has_feature(address_sanitizer) +#if __has_attribute(__no_sanitize__) +#define STBSP__ASAN __attribute__((__no_sanitize__("address"))) +#elif __has_attribute(__no_sanitize_address__) +#define STBSP__ASAN __attribute__((__no_sanitize_address__)) +#elif __has_attribute(__no_address_safety_analysis__) +#define STBSP__ASAN __attribute__((__no_address_safety_analysis__)) +#endif +#endif +#endif +#elif defined(__GNUC__) && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)) +#if defined(__SANITIZE_ADDRESS__) && __SANITIZE_ADDRESS__ +#define STBSP__ASAN __attribute__((__no_sanitize_address__)) +#endif +#endif + +#ifndef STBSP__ASAN +#define STBSP__ASAN +#endif + +#ifdef STB_SPRINTF_STATIC +#define STBSP__PUBLICDEC static +#define STBSP__PUBLICDEF static STBSP__ASAN +#else +#ifdef __cplusplus +#define STBSP__PUBLICDEC extern "C" +#define STBSP__PUBLICDEF extern "C" STBSP__ASAN +#else +#define STBSP__PUBLICDEC extern +#define STBSP__PUBLICDEF STBSP__ASAN +#endif +#endif + +#if defined(__has_attribute) +#if __has_attribute(format) +#define STBSP__ATTRIBUTE_FORMAT(fmt,va) __attribute__((format(printf,fmt,va))) +#endif +#endif + +#ifndef STBSP__ATTRIBUTE_FORMAT +#define STBSP__ATTRIBUTE_FORMAT(fmt,va) +#endif + +#ifdef _MSC_VER +#define STBSP__NOTUSED(v) (void)(v) +#else +#define STBSP__NOTUSED(v) (void)sizeof(v) +#endif + +#include // for va_arg(), va_list() +#include // size_t, ptrdiff_t + +#ifndef STB_SPRINTF_MIN +#define STB_SPRINTF_MIN 512 // how many characters per callback +#endif +typedef char *STBSP_SPRINTFCB(const char *buf, void *user, int len); + +#ifndef STB_SPRINTF_DECORATE +#define STB_SPRINTF_DECORATE(name) stbsp_##name // define this before including if you want to change the names +#endif + +STBSP__PUBLICDEC int STB_SPRINTF_DECORATE(vsprintf)(char *buf, char const *fmt, va_list va); +STBSP__PUBLICDEC int STB_SPRINTF_DECORATE(vsnprintf)(char *buf, int count, char const *fmt, va_list va); +STBSP__PUBLICDEC int STB_SPRINTF_DECORATE(sprintf)(char *buf, char const *fmt, ...) STBSP__ATTRIBUTE_FORMAT(2,3); +STBSP__PUBLICDEC int STB_SPRINTF_DECORATE(snprintf)(char *buf, int count, char const *fmt, ...) STBSP__ATTRIBUTE_FORMAT(3,4); + +STBSP__PUBLICDEC int STB_SPRINTF_DECORATE(vsprintfcb)(STBSP_SPRINTFCB *callback, void *user, char *buf, char const *fmt, va_list va); +STBSP__PUBLICDEC void STB_SPRINTF_DECORATE(set_separators)(char comma, char period); + +#endif //BASE_H diff --git a/build.bat b/build.bat new file mode 100644 index 0000000..02eb928 --- /dev/null +++ b/build.bat @@ -0,0 +1,10 @@ +@echo off + +set src=%cd% +set opts=-nologo -Zi -Fetest + +if not exist "build" mkdir build + +pushd build +cl %opts% %src%\test.c +popd diff --git a/build.sh b/build.sh new file mode 100644 index 0000000..b7cf6a0 --- /dev/null +++ b/build.sh @@ -0,0 +1,12 @@ +#!/bin/bash + +src=$PWD +opts=-Wno-switch + +mkdir -p "build" + +cd build +clang $opts $src/test.c --output test +cd .. + + diff --git a/test.c b/test.c new file mode 100644 index 0000000..fb262d1 --- /dev/null +++ b/test.c @@ -0,0 +1,25 @@ +//#define BLANK_MODE "aritynode.blank.c" + + + +#include "base.h" +#include "aritynode.h" +#include "base.c" +#include "aritynode.test.c" + +#ifndef BLANK_MODE +# include "aritynode.c" +#endif + +#ifdef BLANK_MODE +# include BLANK_MODE +#endif + +#include + +int +main(int argc, char **argv){ + ds_aritynode__test(); + fprintf(stdout, "Completed tests without problem\n"); + return(0); +}