@dekobon/tree-sitter-groovy 0.2.0

package/src/scanner.c

@@ -0,0 +1,213 @@
+// Hand-written external scanner for tree-sitter-groovy.
+//
+// Handles §6.2 slashy-string-start and §6.6 line/block/groovydoc
+// comments. Both start with `/`; combining the dispatch keeps the
+// in-grammar lexer from partially consuming the leading `/`.
+//
+// Stateless — `create` returns NULL and the runtime calls
+// `destroy` / `serialize` / `deserialize` as no-ops. When a future
+// branch needs persistent state, introduce a struct then.
+
+#include "tree_sitter/parser.h"
+
+enum TokenType {
+    SLASHY_STRING_START,
+    LINE_COMMENT,
+    BLOCK_COMMENT,
+    GROOVYDOC_COMMENT,
+};
+
+static inline void advance(TSLexer *lexer) {
+    lexer->advance(lexer, false);
+}
+
+static inline bool is_whitespace(int32_t c) {
+    return c == ' ' || c == '\t' || c == '\n' || c == '\r';
+}
+
+void *tree_sitter_groovy_external_scanner_create(void) {
+    return NULL;
+}
+
+void tree_sitter_groovy_external_scanner_destroy(void *payload) {
+    (void)payload;
+}
+
+unsigned tree_sitter_groovy_external_scanner_serialize(
+    void *payload,
+    char *buffer
+) {
+    (void)payload;
+    (void)buffer;
+    return 0;
+}
+
+void tree_sitter_groovy_external_scanner_deserialize(
+    void *payload,
+    const char *buffer,
+    unsigned length
+) {
+    (void)payload;
+    (void)buffer;
+    (void)length;
+}
+
+bool tree_sitter_groovy_external_scanner_scan(
+    void *payload,
+    TSLexer *lexer,
+    const bool *valid_symbols
+) {
+    (void)payload;
+
+    // SPECIFICATION.md §6.6 — line / block / groovydoc comments
+    // and §6.2 slashy strings. Both start with `/`; combining their
+    // dispatch keeps the in-grammar lexer from partially consuming
+    // the leading `/`. Leading whitespace is skipped via
+    // advance(true) so the scanner gets a chance to fire after the
+    // in-grammar `\s` SKIP rule — without this, tree-sitter's lexer
+    // eats `\n`, does NOT re-invoke the external scanner, then
+    // fails on the following `/` and consumes it through error
+    // recovery.
+    bool wants_comment = valid_symbols[LINE_COMMENT]
+        || valid_symbols[BLOCK_COMMENT]
+        || valid_symbols[GROOVYDOC_COMMENT];
+    bool wants_slashy = valid_symbols[SLASHY_STRING_START];
+    if (!wants_comment && !wants_slashy) {
+        return false;
+    }
+
+    while (is_whitespace(lexer->lookahead)) {
+        lexer->advance(lexer, true);
+    }
+    if (lexer->lookahead != '/') {
+        return false;
+    }
+
+    advance(lexer);
+    // Dispatch on the char after `/`:
+    //   `/`  → line comment
+    //   `*`  → block / groovydoc comment
+    //   `=`  → augmented assign, in-grammar handles it
+    //   else → slashy string (when valid_symbols allow)
+    int32_t next = lexer->lookahead;
+    if (next == '/') {
+        if (!valid_symbols[LINE_COMMENT]) {
+            return false;
+        }
+        advance(lexer);
+        // EOF-bounded loop: lexer->eof() guarantees termination on
+        // unterminated input. Do not tighten without preserving the
+        // EOF guard.
+        while (!lexer->eof(lexer) && lexer->lookahead != '\n') {
+            advance(lexer);
+        }
+        lexer->result_symbol = LINE_COMMENT;
+        return true;
+    }
+    if (next == '*') {
+        if (!wants_comment) {
+            return false;
+        }
+        advance(lexer);
+        bool is_groovydoc = false;
+        if (lexer->lookahead == '*') {
+            advance(lexer);
+            is_groovydoc = true;
+            if (lexer->lookahead == '/') {
+                advance(lexer);
+                if (!valid_symbols[GROOVYDOC_COMMENT]) {
+                    return false;
+                }
+                lexer->result_symbol = GROOVYDOC_COMMENT;
+                return true;
+            }
+        }
+        // EOF-bounded loop: a `/* …` without a closer terminates
+        // here via lexer->eof(), not by going past end-of-input.
+        while (!lexer->eof(lexer)) {
+            if (lexer->lookahead == '*') {
+                advance(lexer);
+                if (lexer->lookahead == '/') {
+                    advance(lexer);
+                    if (is_groovydoc) {
+                        if (!valid_symbols[GROOVYDOC_COMMENT]) {
+                            return false;
+                        }
+                        lexer->result_symbol = GROOVYDOC_COMMENT;
+                    } else {
+                        if (!valid_symbols[BLOCK_COMMENT]) {
+                            return false;
+                        }
+                        lexer->result_symbol = BLOCK_COMMENT;
+                    }
+                    return true;
+                }
+            } else {
+                advance(lexer);
+            }
+        }
+        return false;
+    }
+    if (next == '=') {
+        // `/=` is the augmented-assign operator. The in-grammar
+        // lexer owns it. Returning false here causes tree-sitter
+        // to rewind the cursor to before the leading `/`, so the
+        // in-grammar lexer can match `/=` cleanly.
+        return false;
+    }
+    // Slashy string opening `/` — we've consumed it; the body and
+    // closing `/` are matched by the grammar's `slashy_string` rule
+    // via regex tokens, so `$identifier` and `${expr}` segments can
+    // be exposed as structured children. SPECIFICATION.md §5.4 /
+    // §6.2 require a context-sensitive emit. Three pragmatic guards
+    // keep `a / b` and similar division contexts from being
+    // mis-tokenised as the opening of a slashy:
+    //
+    //   (1) Reject an empty body (the next char after the opening
+    //       `/` is a closing `/`) — `//` is already a line comment
+    //       and `/=` is already trapped above, so an empty slashy
+    //       is excluded.
+    //   (2) Reject a body that starts with whitespace — `a / b`
+    //       has a space immediately after the operator `/`, but
+    //       every legal slashy regex starts with a non-whitespace
+    //       char.
+    //   (3) Look ahead through the body to confirm there is a
+    //       closing `/` on the same line. Without this, `a / b\nc`
+    //       at end of file would emit a slashy opener and leave
+    //       the body unterminated.
+    if (!wants_slashy) {
+        return false;
+    }
+    if (lexer->lookahead == '/' || is_whitespace(lexer->lookahead)) {
+        return false;
+    }
+    // Look ahead (without consuming) to confirm a closing `/` exists
+    // before a newline or EOF. `lexer->mark_end` records the position
+    // where the slashy opener token ends; advancing past it during
+    // look-ahead does not extend the token range as long as we do
+    // not call `mark_end` again.
+    lexer->mark_end(lexer);
+    bool found_close = false;
+    while (!lexer->eof(lexer)) {
+        if (lexer->lookahead == '\\') {
+            advance(lexer);
+            if (!lexer->eof(lexer)) {
+                advance(lexer);
+            }
+            continue;
+        }
+        if (lexer->lookahead == '/') {
+            found_close = true;
+            break;
+        }
+        if (lexer->lookahead == '\n' || lexer->lookahead == '\r') {
+            break;
+        }
+        advance(lexer);
+    }
+    if (!found_close) {
+        return false;
+    }
+    lexer->result_symbol = SLASHY_STRING_START;
+    return true;
+}

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 +1,291 @@
+#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) \
+  _array__reserve((Array *)(self), 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))
+
+/// 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))
+
+/// 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)); \
+    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, contents)                    \
+  _array__splice(                                               \
+    (Array *)(self), array_elem_size(self), (self)->size, \
+    0, count,  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                                 \
+  )
+
+/// 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))
+
+/// Remove one element from the array at the given `index`.
+#define array_erase(self, _index) \
+  _array__erase((Array *)(self), 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))
+
+/// Swap one array with another
+#define array_swap(self, other) \
+  _array__swap((Array *)(self), (Array *)(other))
+
+/// 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
+
+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;
+  }
+}
+
+/// 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;
+  memmove(contents + index * element_size, contents + (index + 1) * element_size,
+          (self->size - index - 1) * element_size);
+  self->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);
+    } else {
+      self->contents = ts_malloc(new_capacity * element_size);
+    }
+    self->capacity = new_capacity;
+  }
+}
+
+/// 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);
+}
+
+/// 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;
+}
+
+/// 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;
+    if (new_capacity < 8) new_capacity = 8;
+    if (new_capacity < new_size) new_capacity = new_size;
+    _array__reserve(self, element_size, new_capacity);
+  }
+}
+
+/// This is not what you're looking for, see `array_splice`.
+static inline void _array__splice(Array *self, 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 old_end = index + old_count;
+  uint32_t new_end = index + new_count;
+  assert(old_end <= self->size);
+
+  _array__reserve(self, element_size, new_size);
+
+  char *contents = (char *)self->contents;
+  if (self->size > old_end) {
+    memmove(
+      contents + new_end * element_size,
+      contents + old_end * element_size,
+      (self->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
+      );
+    }
+  }
+  self->size += new_count - old_count;
+}
+
+/// 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_