tree-sitter-ktav 0.2.1

package/src/scanner.c

@@ -0,0 +1,209 @@
+// Tree-sitter external scanner for Ktav.
+//
+// Emits four tokens that the LR(1) grammar generated from grammar.js
+// cannot express on its own:
+//
+//   _marker_ws  — a zero-width assertion that fires only when the
+//                 byte immediately following a pair separator
+//                 (`:`, `::`, `:i`, `:f`) is ASCII whitespace
+//                 (space, tab, CR, LF) or EOF. The assertion is
+//                 zero-width — it does not consume any input — so
+//                 the existing `extras` whitespace handling and the
+//                 `_newline` rule for empty values both still apply
+//                 unchanged. Its sole purpose is to MAKE A PARSE FAIL
+//                 when a writer omits the mandatory whitespace, e.g.
+//                 `key:value` (§ 6.10 of the spec).
+//
+//   _strict_eol — consumes `[ \t]*` followed by `\r?\n` OR by EOF.
+//                 Used as the line terminator for compound closers
+//                 (`}`, `]`) so that any non-whitespace content
+//                 between the closer and the line terminator
+//                 causes a parse failure (§ 5.6.1 closer-on-its-own-
+//                 line and the cleanliness rule for object/array
+//                 closers).
+//
+//   _stripped_close  — context-sensitive closer for `(...)` multi-line
+//                      strings. Matches `)` followed by `[ \t]*\r?\n`
+//                      (or EOF). Only valid inside the body of a
+//                      `multiline_stripped`. A `))` line in that
+//                      context is NOT a close — the scanner declines
+//                      and the line falls through to the
+//                      `multiline_content_line` regex token.
+//
+//   _verbatim_close  — context-sensitive closer for `((...))` multi-line
+//                      strings. Matches `))` followed by `[ \t]*\r?\n`
+//                      (or EOF). Only valid inside `multiline_verbatim`.
+//                      A single `)` line in that context falls through
+//                      to `multiline_content_line`.
+//
+// All tokens are stateless: the parser supplies the necessary context
+// via `valid_symbols`. The external_scanner_state size is therefore
+// zero, and serialize / deserialize are no-ops.
+
+#include "tree_sitter/parser.h"
+
+enum TokenType {
+    MARKER_WS,
+    STRICT_EOL,
+    STRIPPED_CLOSE,
+    VERBATIM_CLOSE,
+};
+
+void *tree_sitter_ktav_external_scanner_create(void) {
+    return NULL;
+}
+
+void tree_sitter_ktav_external_scanner_destroy(void *payload) {
+    (void)payload;
+}
+
+unsigned tree_sitter_ktav_external_scanner_serialize(void *payload, char *buffer) {
+    (void)payload;
+    (void)buffer;
+    return 0;
+}
+
+void tree_sitter_ktav_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
+    (void)payload;
+    (void)buffer;
+    (void)length;
+}
+
+static inline bool is_h_ws(int32_t c) {
+    return c == ' ' || c == '\t';
+}
+
+// Consume optional `[ \t]*` then a single line terminator (LF, CRLF,
+// or EOF). Returns true on success and leaves `mark_end` at the byte
+// after the terminator. Returns false (without disturbing mark_end's
+// previous position) if the next non-h-ws byte is not a terminator.
+static bool consume_line_terminator(TSLexer *lexer) {
+    while (is_h_ws(lexer->lookahead)) {
+        lexer->advance(lexer, false);
+    }
+    int32_t c = lexer->lookahead;
+    if (c == '\n') {
+        lexer->advance(lexer, false);
+        lexer->mark_end(lexer);
+        return true;
+    }
+    if (c == '\r') {
+        lexer->advance(lexer, false);
+        if (lexer->lookahead == '\n') {
+            lexer->advance(lexer, false);
+        }
+        lexer->mark_end(lexer);
+        return true;
+    }
+    if (c == 0) {
+        lexer->mark_end(lexer);
+        return true;
+    }
+    return false;
+}
+
+bool tree_sitter_ktav_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
+    (void)payload;
+
+    // Mark the current lex position before any `advance` so that on
+    // failure we don't leave bytes consumed (which would corrupt the
+    // lexer state for the next attempted token).
+    lexer->mark_end(lexer);
+
+    // _marker_ws — zero-width. Succeed iff the next byte is horizontal
+    // whitespace, CR, LF, or EOF. We don't `advance`; we only `mark_end`
+    // at the current position so the token has zero length.
+    if (valid_symbols[MARKER_WS]) {
+        int32_t c = lexer->lookahead;
+        if (c == ' ' || c == '\t' || c == '\n' || c == '\r' || c == 0) {
+            lexer->mark_end(lexer);
+            lexer->result_symbol = MARKER_WS;
+            return true;
+        }
+        // _marker_ws is the only valid token here in the strict path —
+        // returning false makes tree-sitter raise a parse error, which
+        // is exactly the § 6.10 rejection we want. The two branches are
+        // mutually exclusive: never fall through to STRICT_EOL.
+        return false;
+    }
+
+    // _verbatim_close — matches `[ \t]*))[ \t]*\r?\n` (or EOF). The
+    // closer may have leading horizontal whitespace (the `)` is "on its
+    // own line, possibly with leading whitespace" per § 5.6.1). Only
+    // valid inside the body of a `multiline_verbatim`. Tried before
+    // STRIPPED_CLOSE so `))` is never split into a `)` close + leftover.
+    // (In practice the two are mutually exclusive per parse state, so
+    // ordering matters only for defensive correctness.)
+    if (valid_symbols[VERBATIM_CLOSE]) {
+        while (is_h_ws(lexer->lookahead)) {
+            lexer->advance(lexer, false);
+        }
+        if (lexer->lookahead == ')') {
+            lexer->advance(lexer, false);
+            if (lexer->lookahead == ')') {
+                lexer->advance(lexer, false);
+                if (consume_line_terminator(lexer)) {
+                    lexer->result_symbol = VERBATIM_CLOSE;
+                    return true;
+                }
+            }
+        }
+        // Fall through: a non-`))` line inside verbatim becomes content.
+        return false;
+    }
+
+    // _stripped_close — matches `[ \t]*)[ \t]*\r?\n` (or EOF). Only
+    // valid inside `multiline_stripped`. A `))` line is NOT a stripped
+    // close: we require the byte after the first `)` to NOT be another
+    // `)`, so `))` falls through to the `multiline_content_line`
+    // regex token.
+    if (valid_symbols[STRIPPED_CLOSE]) {
+        while (is_h_ws(lexer->lookahead)) {
+            lexer->advance(lexer, false);
+        }
+        if (lexer->lookahead == ')') {
+            lexer->advance(lexer, false);
+            if (lexer->lookahead != ')') {
+                if (consume_line_terminator(lexer)) {
+                    lexer->result_symbol = STRIPPED_CLOSE;
+                    return true;
+                }
+            }
+        }
+        return false;
+    }
+
+    // _strict_eol — consume optional horizontal whitespace, then the
+    // line terminator (LF, CRLF, or EOF). If a non-whitespace byte
+    // appears before the line terminator, fail.
+    if (valid_symbols[STRICT_EOL]) {
+        while (is_h_ws(lexer->lookahead)) {
+            lexer->advance(lexer, false);
+        }
+        int32_t c = lexer->lookahead;
+        if (c == '\n') {
+            lexer->advance(lexer, false);
+            lexer->mark_end(lexer);
+            lexer->result_symbol = STRICT_EOL;
+            return true;
+        }
+        if (c == '\r') {
+            lexer->advance(lexer, false);
+            if (lexer->lookahead == '\n') {
+                lexer->advance(lexer, false);
+            }
+            lexer->mark_end(lexer);
+            lexer->result_symbol = STRICT_EOL;
+            return true;
+        }
+        if (c == 0) {
+            // EOF as a line terminator (§ 3.2: trailing content of the
+            // final line need not be followed by a line separator).
+            lexer->mark_end(lexer);
+            lexer->result_symbol = STRICT_EOL;
+            return true;
+        }
+    }
+
+    return false;
+}

package/src/tree_sitter/alloc.h

@@ -0,0 +1,54 @@
+#ifndef TREE_SITTER_ALLOC_H_
+#define TREE_SITTER_ALLOC_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+// Allow clients to override allocation functions
+#ifdef TREE_SITTER_REUSE_ALLOCATOR
+
+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
+#endif
+#ifndef ts_calloc
+#define ts_calloc  ts_current_calloc
+#endif
+#ifndef ts_realloc
+#define ts_realloc ts_current_realloc
+#endif
+#ifndef ts_free
+#define ts_free    ts_current_free
+#endif
+
+#else
+
+#ifndef ts_malloc
+#define ts_malloc  malloc
+#endif
+#ifndef ts_calloc
+#define ts_calloc  calloc
+#endif
+#ifndef ts_realloc
+#define ts_realloc realloc
+#endif
+#ifndef ts_free
+#define ts_free    free
+#endif
+
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif // TREE_SITTER_ALLOC_H_

package/src/tree_sitter/array.h

@@ -0,0 +1,330 @@
+#ifndef TREE_SITTER_ARRAY_H_
+#define TREE_SITTER_ARRAY_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "./alloc.h"
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifdef _MSC_VER
+#pragma warning(push)
+#pragma warning(disable : 4101)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#endif
+
+#define Array(T)       \
+  struct {             \
+    T *contents;       \
+    uint32_t size;     \
+    uint32_t capacity; \
+  }
+
+/// Initialize an array.
+#define array_init(self) \
+  ((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
+
+/// Create an empty array.
+#define array_new() \
+  { NULL, 0, 0 }
+
+/// Get a pointer to the element at a given `index` in the array.
+#define array_get(self, _index) \
+  (assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
+
+/// Get a pointer to the first element in the array.
+#define array_front(self) array_get(self, 0)
+
+/// Get a pointer to the last element in the array.
+#define array_back(self) array_get(self, (self)->size - 1)
+
+/// Clear the array, setting its size to zero. Note that this does not free any
+/// memory allocated for the array's contents.
+#define array_clear(self) ((self)->size = 0)
+
+/// 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)        \
+  ((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)                           \
+  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)                                 \
+  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;                                                     \
+    (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);                                                     \
+  } while (0)
+
+/// Append all elements from one array to the end of another.
+#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, 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) \
+  (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)                     \
+  (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((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)                                   \
+  (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)                                     \
+  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)
+
+/// Search a sorted array for a given `needle` value, using the given `compare`
+/// callback to determine the order.
+///
+/// If an existing element is found to be equal to `needle`, then the `index`
+/// out-parameter is set to the existing value's index, and the `exists`
+/// out-parameter is set to true. Otherwise, `index` is set to an index where
+/// `needle` should be inserted in order to preserve the sorting, and `exists`
+/// is set to false.
+#define array_search_sorted_with(self, compare, needle, _index, _exists) \
+  _array__search_sorted(self, 0, compare, , needle, _index, _exists)
+
+/// Search a sorted array for a given `needle` value, using integer comparisons
+/// of a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_with`.
+#define array_search_sorted_by(self, field, needle, _index, _exists) \
+  _array__search_sorted(self, 0, _compare_int, field, needle, _index, _exists)
+
+/// Insert a given `value` into a sorted array, using the given `compare`
+/// callback to determine the order.
+#define array_insert_sorted_with(self, compare, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_with(self, compare, &(value), &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+/// Insert a given `value` into a sorted array, using integer comparisons of
+/// a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_by`.
+#define array_insert_sorted_by(self, field, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_by(self, field, (value) field, &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+// Private
+
+// 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(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,
+          (*size - index - 1) * element_size);
+  (*size)--;
+}
+
+/// This is not what you're looking for, see `array_reserve`.
+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 {
+      new_contents = ts_malloc(new_capacity * element_size);
+    }
+    *capacity = new_capacity;
+  }
+  return new_contents;
+}
+
+/// This is not what you're looking for, see `array_assign`.
+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(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(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;
+    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(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 = *size + new_count - old_count;
+  uint32_t old_end = index + old_count;
+  uint32_t new_end = index + new_count;
+  assert(old_end <= *size);
+
+  void *new_contents = _array__reserve(self_contents, capacity, element_size, new_size);
+
+  char *contents = (char *)new_contents;
+  if (*size > old_end) {
+    memmove(
+      contents + new_end * element_size,
+      contents + old_end * element_size,
+      (*size - old_end) * element_size
+    );
+  }
+  if (new_count > 0) {
+    if (elements) {
+      memcpy(
+        (contents + index * element_size),
+        elements,
+        new_count * element_size
+      );
+    } else {
+      memset(
+        (contents + index * element_size),
+        0,
+        new_count * element_size
+      );
+    }
+  }
+  *size += new_count - old_count;
+
+  return new_contents;
+}
+
+/// A binary search routine, based on Rust's `std::slice::binary_search_by`.
+/// This is not what you're looking for, see `array_search_sorted_with` or `array_search_sorted_by`.
+#define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \
+  do { \
+    *(_index) = start; \
+    *(_exists) = false; \
+    uint32_t size = (self)->size - *(_index); \
+    if (size == 0) break; \
+    int comparison; \
+    while (size > 1) { \
+      uint32_t half_size = size / 2; \
+      uint32_t mid_index = *(_index) + half_size; \
+      comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \
+      if (comparison <= 0) *(_index) = mid_index; \
+      size -= half_size; \
+    } \
+    comparison = compare(&((self)->contents[*(_index)] suffix), (needle)); \
+    if (comparison == 0) *(_exists) = true; \
+    else if (comparison < 0) *(_index) += 1; \
+  } while (0)
+
+/// Helper macro for the `_sorted_by` routines below. This takes the left (existing)
+/// parameter by reference in order to work with the generic sorting function above.
+#define _compare_int(a, b) ((int)*(a) - (int)(b))
+
+#ifdef _MSC_VER
+#pragma warning(pop)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // TREE_SITTER_ARRAY_H_