@algosail/tree-sitter 0.1.0 → 0.1.2

package/src/tree_sitter/alloc.h

@@ -12,10 +12,10 @@ extern "C" {
 // Allow clients to override allocation functions
 #ifdef TREE_SITTER_REUSE_ALLOCATOR
 
-extern void *(*ts_current_malloc)(size_t);
-extern void *(*ts_current_calloc)(size_t, size_t);
-extern void *(*ts_current_realloc)(void *, size_t);
-extern void (*ts_current_free)(void *);
+extern void *(*ts_current_malloc)(size_t size);
+extern void *(*ts_current_calloc)(size_t count, size_t size);
+extern void *(*ts_current_realloc)(void *ptr, size_t size);
+extern void (*ts_current_free)(void *ptr);
 
 #ifndef ts_malloc
 #define ts_malloc  ts_current_malloc

package/src/tree_sitter/array.h

@@ -14,6 +14,7 @@ extern "C" {
 #include <string.h>
 
 #ifdef _MSC_VER
+#pragma warning(push)
 #pragma warning(disable : 4101)
 #elif defined(__GNUC__) || defined(__clang__)
 #pragma GCC diagnostic push
@@ -51,67 +52,96 @@ extern "C" {
 
 /// Reserve `new_capacity` elements of space in the array. If `new_capacity` is
 /// less than the array's current capacity, this function has no effect.
-#define array_reserve(self, new_capacity) \
-  _array__reserve((Array *)(self), array_elem_size(self), new_capacity)
+#define array_reserve(self, new_capacity)        \
+  ((self)->contents = _array__reserve(           \
+    (void *)(self)->contents, &(self)->capacity, \
+    array_elem_size(self), new_capacity)         \
+  )
 
 /// Free any memory allocated for this array. Note that this does not free any
 /// memory allocated for the array's contents.
-#define array_delete(self) _array__delete((Array *)(self))
+#define array_delete(self)                           \
+  do {                                               \
+    if ((self)->contents) ts_free((self)->contents); \
+    (self)->contents = NULL;                         \
+    (self)->size = 0;                                \
+    (self)->capacity = 0;                            \
+  } while (0)
 
 /// Push a new `element` onto the end of the array.
-#define array_push(self, element)                            \
-  (_array__grow((Array *)(self), 1, array_elem_size(self)), \
-   (self)->contents[(self)->size++] = (element))
+#define array_push(self, element)                                 \
+  do {                                                            \
+    (self)->contents = _array__grow(                              \
+      (void *)(self)->contents, (self)->size, &(self)->capacity,  \
+      1, array_elem_size(self)                                    \
+    );                                                            \
+   (self)->contents[(self)->size++] = (element);                  \
+  } while(0)
 
 /// Increase the array's size by `count` elements.
 /// New elements are zero-initialized.
-#define array_grow_by(self, count) \
-  do { \
-    if ((count) == 0) break; \
-    _array__grow((Array *)(self), count, array_elem_size(self)); \
+#define array_grow_by(self, count)                                               \
+  do {                                                                           \
+    if ((count) == 0) break;                                                     \
+    (self)->contents = _array__grow(                                             \
+      (self)->contents, (self)->size, &(self)->capacity,                         \
+      count, array_elem_size(self)                                               \
+    );                                                                           \
     memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \
-    (self)->size += (count); \
+    (self)->size += (count);                                                     \
   } while (0)
 
 /// Append all elements from one array to the end of another.
-#define array_push_all(self, other)                                       \
+#define array_push_all(self, other) \
   array_extend((self), (other)->size, (other)->contents)
 
 /// Append `count` elements to the end of the array, reading their values from the
 /// `contents` pointer.
-#define array_extend(self, count, contents)                    \
-  _array__splice(                                               \
-    (Array *)(self), array_elem_size(self), (self)->size, \
-    0, count,  contents                                        \
+#define array_extend(self, count, other_contents)                 \
+  (self)->contents = _array__splice(                              \
+    (void*)(self)->contents, &(self)->size, &(self)->capacity,    \
+    array_elem_size(self), (self)->size, 0, count, other_contents \
   )
 
 /// Remove `old_count` elements from the array starting at the given `index`. At
 /// the same index, insert `new_count` new elements, reading their values from the
 /// `new_contents` pointer.
-#define array_splice(self, _index, old_count, new_count, new_contents)  \
-  _array__splice(                                                       \
-    (Array *)(self), array_elem_size(self), _index,                \
-    old_count, new_count, new_contents                                 \
+#define array_splice(self, _index, old_count, new_count, new_contents) \
+  (self)->contents = _array__splice(                                   \
+    (void *)(self)->contents, &(self)->size, &(self)->capacity,        \
+    array_elem_size(self), _index, old_count, new_count, new_contents  \
   )
 
 /// Insert one `element` into the array at the given `index`.
-#define array_insert(self, _index, element) \
-  _array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, &(element))
+#define array_insert(self, _index, element)                     \
+  (self)->contents = _array__splice(                            \
+    (void *)(self)->contents, &(self)->size, &(self)->capacity, \
+    array_elem_size(self), _index, 0, 1, &(element)             \
+  )
 
 /// Remove one element from the array at the given `index`.
 #define array_erase(self, _index) \
-  _array__erase((Array *)(self), array_elem_size(self), _index)
+  _array__erase((void *)(self)->contents, &(self)->size, array_elem_size(self), _index)
 
 /// Pop the last element off the array, returning the element by value.
 #define array_pop(self) ((self)->contents[--(self)->size])
 
 /// Assign the contents of one array to another, reallocating if necessary.
-#define array_assign(self, other) \
-  _array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
+#define array_assign(self, other)                                   \
+  (self)->contents = _array__assign(                                \
+    (void *)(self)->contents, &(self)->size, &(self)->capacity,     \
+    (const void *)(other)->contents, (other)->size, array_elem_size(self) \
+  )
 
 /// Swap one array with another
-#define array_swap(self, other) \
-  _array__swap((Array *)(self), (Array *)(other))
+#define array_swap(self, other)                                     \
+  do {                                                              \
+    void *_array_swap_tmp = (void *)(self)->contents;               \
+    (self)->contents = (other)->contents;                           \
+    (other)->contents = _array_swap_tmp;                            \
+    _array__swap(&(self)->size, &(self)->capacity,                  \
+                 &(other)->size, &(other)->capacity);               \
+  } while (0)
 
 /// Get the size of the array contents
 #define array_elem_size(self) (sizeof *(self)->contents)
@@ -156,82 +186,90 @@ extern "C" {
 
 // Private
 
-typedef Array(void) Array;
-
-/// This is not what you're looking for, see `array_delete`.
-static inline void _array__delete(Array *self) {
-  if (self->contents) {
-    ts_free(self->contents);
-    self->contents = NULL;
-    self->size = 0;
-    self->capacity = 0;
-  }
-}
+// Pointers to individual `Array` fields (rather than the entire `Array` itself)
+// are passed to the various `_array__*` functions below to address strict aliasing
+// violations that arises when the _entire_ `Array` struct is passed as `Array(void)*`.
+//
+// The `Array` type itself was not altered as a solution in order to avoid breakage
+// with existing consumers (in particular, parsers with external scanners).
 
 /// This is not what you're looking for, see `array_erase`.
-static inline void _array__erase(Array *self, size_t element_size,
-                                uint32_t index) {
-  assert(index < self->size);
-  char *contents = (char *)self->contents;
+static inline void _array__erase(void* self_contents, uint32_t *size,
+                                size_t element_size, uint32_t index) {
+  assert(index < *size);
+  char *contents = (char *)self_contents;
   memmove(contents + index * element_size, contents + (index + 1) * element_size,
-          (self->size - index - 1) * element_size);
-  self->size--;
+          (*size - index - 1) * element_size);
+  (*size)--;
 }
 
 /// This is not what you're looking for, see `array_reserve`.
-static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity) {
-  if (new_capacity > self->capacity) {
-    if (self->contents) {
-      self->contents = ts_realloc(self->contents, new_capacity * element_size);
+static inline void *_array__reserve(void *contents, uint32_t *capacity,
+                                  size_t element_size, uint32_t new_capacity) {
+  void *new_contents = contents;
+  if (new_capacity > *capacity) {
+    if (contents) {
+      new_contents = ts_realloc(contents, new_capacity * element_size);
     } else {
-      self->contents = ts_malloc(new_capacity * element_size);
+      new_contents = ts_malloc(new_capacity * element_size);
     }
-    self->capacity = new_capacity;
+    *capacity = new_capacity;
   }
+  return new_contents;
 }
 
 /// This is not what you're looking for, see `array_assign`.
-static inline void _array__assign(Array *self, const Array *other, size_t element_size) {
-  _array__reserve(self, element_size, other->size);
-  self->size = other->size;
-  memcpy(self->contents, other->contents, self->size * element_size);
+static inline void *_array__assign(void* self_contents, uint32_t *self_size, uint32_t *self_capacity,
+                                 const void *other_contents, uint32_t other_size, size_t element_size) {
+  void *new_contents = _array__reserve(self_contents, self_capacity, element_size, other_size);
+  *self_size = other_size;
+  memcpy(new_contents, other_contents, *self_size * element_size);
+  return new_contents;
 }
 
 /// This is not what you're looking for, see `array_swap`.
-static inline void _array__swap(Array *self, Array *other) {
-  Array swap = *other;
-  *other = *self;
-  *self = swap;
+static inline void _array__swap(uint32_t *self_size, uint32_t *self_capacity,
+                               uint32_t *other_size, uint32_t *other_capacity) {
+  uint32_t tmp_size = *self_size;
+  uint32_t tmp_capacity = *self_capacity;
+  *self_size = *other_size;
+  *self_capacity = *other_capacity;
+  *other_size = tmp_size;
+  *other_capacity = tmp_capacity;
 }
 
 /// This is not what you're looking for, see `array_push` or `array_grow_by`.
-static inline void _array__grow(Array *self, uint32_t count, size_t element_size) {
-  uint32_t new_size = self->size + count;
-  if (new_size > self->capacity) {
-    uint32_t new_capacity = self->capacity * 2;
+static inline void *_array__grow(void *contents, uint32_t size, uint32_t *capacity,
+                               uint32_t count, size_t element_size) {
+  void *new_contents = contents;
+  uint32_t new_size = size + count;
+  if (new_size > *capacity) {
+    uint32_t new_capacity = *capacity * 2;
     if (new_capacity < 8) new_capacity = 8;
     if (new_capacity < new_size) new_capacity = new_size;
-    _array__reserve(self, element_size, new_capacity);
+    new_contents = _array__reserve(contents, capacity, element_size, new_capacity);
   }
+  return new_contents;
 }
 
 /// This is not what you're looking for, see `array_splice`.
-static inline void _array__splice(Array *self, size_t element_size,
+static inline void *_array__splice(void *self_contents, uint32_t *size, uint32_t *capacity,
+                                 size_t element_size,
                                  uint32_t index, uint32_t old_count,
                                  uint32_t new_count, const void *elements) {
-  uint32_t new_size = self->size + new_count - old_count;
+  uint32_t new_size = *size + new_count - old_count;
   uint32_t old_end = index + old_count;
   uint32_t new_end = index + new_count;
-  assert(old_end <= self->size);
+  assert(old_end <= *size);
 
-  _array__reserve(self, element_size, new_size);
+  void *new_contents = _array__reserve(self_contents, capacity, element_size, new_size);
 
-  char *contents = (char *)self->contents;
-  if (self->size > old_end) {
+  char *contents = (char *)new_contents;
+  if (*size > old_end) {
     memmove(
       contents + new_end * element_size,
       contents + old_end * element_size,
-      (self->size - old_end) * element_size
+      (*size - old_end) * element_size
     );
   }
   if (new_count > 0) {
@@ -249,7 +287,9 @@ static inline void _array__splice(Array *self, size_t element_size,
       );
     }
   }
-  self->size += new_count - old_count;
+  *size += new_count - old_count;
+
+  return new_contents;
 }
 
 /// A binary search routine, based on Rust's `std::slice::binary_search_by`.
@@ -278,7 +318,7 @@ static inline void _array__splice(Array *self, size_t element_size,
 #define _compare_int(a, b) ((int)*(a) - (int)(b))
 
 #ifdef _MSC_VER
-#pragma warning(default : 4101)
+#pragma warning(pop)
 #elif defined(__GNUC__) || defined(__clang__)
 #pragma GCC diagnostic pop
 #endif

package/src/tree_sitter/parser.h

@@ -18,6 +18,11 @@ typedef uint16_t TSStateId;
 typedef uint16_t TSSymbol;
 typedef uint16_t TSFieldId;
 typedef struct TSLanguage TSLanguage;
+typedef struct TSLanguageMetadata {
+  uint8_t major_version;
+  uint8_t minor_version;
+  uint8_t patch_version;
+} TSLanguageMetadata;
 #endif
 
 typedef struct {
@@ -26,10 +31,11 @@ typedef struct {
   bool inherited;
 } TSFieldMapEntry;
 
+// Used to index the field and supertype maps.
 typedef struct {
   uint16_t index;
   uint16_t length;
-} TSFieldMapSlice;
+} TSMapSlice;
 
 typedef struct {
   bool visible;
@@ -47,6 +53,7 @@ struct TSLexer {
   uint32_t (*get_column)(TSLexer *);
   bool (*is_at_included_range_start)(const TSLexer *);
   bool (*eof)(const TSLexer *);
+  void (*log)(const TSLexer *, const char *, ...);
 };
 
 typedef enum {
@@ -78,6 +85,12 @@ typedef struct {
   uint16_t external_lex_state;
 } TSLexMode;
 
+typedef struct {
+  uint16_t lex_state;
+  uint16_t external_lex_state;
+  uint16_t reserved_word_set_id;
+} TSLexerMode;
+
 typedef union {
   TSParseAction action;
   struct {
@@ -92,7 +105,7 @@ typedef struct {
 } TSCharacterRange;
 
 struct TSLanguage {
-  uint32_t version;
+  uint32_t abi_version;
   uint32_t symbol_count;
   uint32_t alias_count;
   uint32_t token_count;
@@ -108,13 +121,13 @@ struct TSLanguage {
   const TSParseActionEntry *parse_actions;
   const char * const *symbol_names;
   const char * const *field_names;
-  const TSFieldMapSlice *field_map_slices;
+  const TSMapSlice *field_map_slices;
   const TSFieldMapEntry *field_map_entries;
   const TSSymbolMetadata *symbol_metadata;
   const TSSymbol *public_symbol_map;
   const uint16_t *alias_map;
   const TSSymbol *alias_sequences;
-  const TSLexMode *lex_modes;
+  const TSLexerMode *lex_modes;
   bool (*lex_fn)(TSLexer *, TSStateId);
   bool (*keyword_lex_fn)(TSLexer *, TSStateId);
   TSSymbol keyword_capture_token;
@@ -128,15 +141,23 @@ struct TSLanguage {
     void (*deserialize)(void *, const char *, unsigned);
   } external_scanner;
   const TSStateId *primary_state_ids;
+  const char *name;
+  const TSSymbol *reserved_words;
+  uint16_t max_reserved_word_set_size;
+  uint32_t supertype_count;
+  const TSSymbol *supertype_symbols;
+  const TSMapSlice *supertype_map_slices;
+  const TSSymbol *supertype_map_entries;
+  TSLanguageMetadata metadata;
 };
 
-static inline bool set_contains(TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
+static inline bool set_contains(const TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
   uint32_t index = 0;
   uint32_t size = len - index;
   while (size > 1) {
     uint32_t half_size = size / 2;
     uint32_t mid_index = index + half_size;
-    TSCharacterRange *range = &ranges[mid_index];
+    const TSCharacterRange *range = &ranges[mid_index];
     if (lookahead >= range->start && lookahead <= range->end) {
       return true;
     } else if (lookahead > range->end) {
@@ -144,7 +165,7 @@ static inline bool set_contains(TSCharacterRange *ranges, uint32_t len, int32_t
     }
     size -= half_size;
   }
-  TSCharacterRange *range = &ranges[index];
+  const TSCharacterRange *range = &ranges[index];
   return (lookahead >= range->start && lookahead <= range->end);
 }
 

package/binding.gyp

@@ -1,30 +0,0 @@
-{
-  "targets": [
-    {
-      "target_name": "tree_sitter_sail_binding",
-      "dependencies": [
-        "<!(node -p \"require('node-addon-api').targets\"):node_addon_api_except",
-      ],
-      "include_dirs": [
-        "src",
-      ],
-      "sources": [
-        "bindings/node/binding.cc",
-        "src/parser.c",
-        # NOTE: if your language has an external scanner, add it here.
-      ],
-      "conditions": [
-        ["OS!='win'", {
-          "cflags_c": [
-            "-std=c11",
-          ],
-        }, { # OS == "win"
-          "cflags_c": [
-            "/std:c11",
-            "/utf-8",
-          ],
-        }],
-      ],
-    }
-  ]
-}

package/bindings/node/binding.cc

@@ -1,20 +0,0 @@
-#include <napi.h>
-
-typedef struct TSLanguage TSLanguage;
-
-extern "C" TSLanguage *tree_sitter_sail();
-
-// "tree-sitter", "language" hashed with BLAKE2
-const napi_type_tag LANGUAGE_TYPE_TAG = {
-  0x8AF2E5212AD58ABF, 0xD5006CAD83ABBA16
-};
-
-Napi::Object Init(Napi::Env env, Napi::Object exports) {
-    exports["name"] = Napi::String::New(env, "sail");
-    auto language = Napi::External<TSLanguage>::New(env, tree_sitter_sail());
-    language.TypeTag(&LANGUAGE_TYPE_TAG);
-    exports["language"] = language;
-    return exports;
-}
-
-NODE_API_MODULE(tree_sitter_sail_binding, Init)

package/bindings/node/index.d.ts

@@ -1,28 +0,0 @@
-type BaseNode = {
-  type: string;
-  named: boolean;
-};
-
-type ChildNode = {
-  multiple: boolean;
-  required: boolean;
-  types: BaseNode[];
-};
-
-type NodeInfo =
-  | (BaseNode & {
-      subtypes: BaseNode[];
-    })
-  | (BaseNode & {
-      fields: { [name: string]: ChildNode };
-      children: ChildNode[];
-    });
-
-type Language = {
-  name: string;
-  language: unknown;
-  nodeTypeInfo: NodeInfo[];
-};
-
-declare const language: Language;
-export = language;

package/bindings/node/index.js

@@ -1,7 +0,0 @@
-const root = require("path").join(__dirname, "..", "..");
-
-module.exports = require("node-gyp-build")(root);
-
-try {
-  module.exports.nodeTypeInfo = require("../../src/node-types.json");
-} catch (_) {}