@ast-grep/lang-javascript 0.0.2

package/src/scanner.c

@@ -0,0 +1,364 @@
+#include "tree_sitter/parser.h"
+
+#include <stdio.h>
+#include <wctype.h>
+
+enum TokenType {
+    AUTOMATIC_SEMICOLON,
+    TEMPLATE_CHARS,
+    TERNARY_QMARK,
+    HTML_COMMENT,
+    LOGICAL_OR,
+    ESCAPE_SEQUENCE,
+    REGEX_PATTERN,
+    JSX_TEXT,
+};
+
+void *tree_sitter_javascript_external_scanner_create() { return NULL; }
+
+void tree_sitter_javascript_external_scanner_destroy(void *p) {}
+
+unsigned tree_sitter_javascript_external_scanner_serialize(void *payload, char *buffer) { return 0; }
+
+void tree_sitter_javascript_external_scanner_deserialize(void *p, const char *b, unsigned n) {}
+
+static inline void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
+
+static inline void skip(TSLexer *lexer) { lexer->advance(lexer, true); }
+
+static bool scan_template_chars(TSLexer *lexer) {
+    lexer->result_symbol = TEMPLATE_CHARS;
+    for (bool has_content = false;; has_content = true) {
+        lexer->mark_end(lexer);
+        switch (lexer->lookahead) {
+            case '`':
+                return has_content;
+            case '\0':
+                return false;
+            case '$':
+                advance(lexer);
+                if (lexer->lookahead == '{') {
+                    return has_content;
+                }
+                break;
+            case '\\':
+                return has_content;
+            default:
+                advance(lexer);
+        }
+    }
+}
+
+typedef enum {
+    REJECT,     // Semicolon is illegal, ie a syntax error occurred
+    NO_NEWLINE, // Unclear if semicolon will be legal, continue
+    ACCEPT,     // Semicolon is legal, assuming a comment was encountered
+} WhitespaceResult;
+
+/**
+ * @param consume If false, only consume enough to check if comment indicates semicolon-legality
+ */
+static WhitespaceResult scan_whitespace_and_comments(TSLexer *lexer, bool *scanned_comment, bool consume) {
+    bool saw_block_newline = false;
+
+    for (;;) {
+        while (iswspace(lexer->lookahead)) {
+            skip(lexer);
+        }
+
+        if (lexer->lookahead == '/') {
+            skip(lexer);
+
+            if (lexer->lookahead == '/') {
+                skip(lexer);
+                while (lexer->lookahead != 0 && lexer->lookahead != '\n' && lexer->lookahead != 0x2028 &&
+                       lexer->lookahead != 0x2029) {
+                    skip(lexer);
+                }
+                *scanned_comment = true;
+            } else if (lexer->lookahead == '*') {
+                skip(lexer);
+                while (lexer->lookahead != 0) {
+                    if (lexer->lookahead == '*') {
+                        skip(lexer);
+                        if (lexer->lookahead == '/') {
+                            skip(lexer);
+                            *scanned_comment = true;
+
+                            if (lexer->lookahead != '/' && !consume) {
+                                return saw_block_newline ? ACCEPT : NO_NEWLINE;
+                            }
+
+                            break;
+                        }
+                    } else if (lexer->lookahead == '\n' || lexer->lookahead == 0x2028 || lexer->lookahead == 0x2029) {
+                        saw_block_newline = true;
+                        skip(lexer);
+                    } else {
+                        skip(lexer);
+                    }
+                }
+            } else {
+                return REJECT;
+            }
+        } else {
+            return ACCEPT;
+        }
+    }
+}
+
+static bool scan_automatic_semicolon(TSLexer *lexer, bool comment_condition, bool *scanned_comment) {
+    lexer->result_symbol = AUTOMATIC_SEMICOLON;
+    lexer->mark_end(lexer);
+
+    for (;;) {
+        if (lexer->lookahead == 0) {
+            return true;
+        }
+
+        if (lexer->lookahead == '/') {
+            WhitespaceResult result = scan_whitespace_and_comments(lexer, scanned_comment, false);
+            if (result == REJECT) {
+                return false;
+            }
+
+            if (result == ACCEPT && comment_condition && lexer->lookahead != ',' && lexer->lookahead != '=') {
+                return true;
+            }
+        }
+
+        if (lexer->lookahead == '}') {
+            return true;
+        }
+
+        if (lexer->is_at_included_range_start(lexer)) {
+            return true;
+        }
+
+        if (lexer->lookahead == '\n' || lexer->lookahead == 0x2028 || lexer->lookahead == 0x2029) {
+            break;
+        }
+
+        if (!iswspace(lexer->lookahead)) {
+            return false;
+        }
+
+        skip(lexer);
+    }
+
+    skip(lexer);
+
+    if (scan_whitespace_and_comments(lexer, scanned_comment, true) == REJECT) {
+        return false;
+    }
+
+    switch (lexer->lookahead) {
+        case '`':
+        case ',':
+        case ':':
+        case ';':
+        case '*':
+        case '%':
+        case '>':
+        case '<':
+        case '=':
+        case '[':
+        case '(':
+        case '?':
+        case '^':
+        case '|':
+        case '&':
+        case '/':
+            return false;
+
+        // Insert a semicolon before decimals literals but not otherwise.
+        case '.':
+            skip(lexer);
+            return iswdigit(lexer->lookahead);
+
+        // Insert a semicolon before `--` and `++`, but not before binary `+` or `-`.
+        case '+':
+            skip(lexer);
+            return lexer->lookahead == '+';
+        case '-':
+            skip(lexer);
+            return lexer->lookahead == '-';
+
+        // Don't insert a semicolon before `!=`, but do insert one before a unary `!`.
+        case '!':
+            skip(lexer);
+            return lexer->lookahead != '=';
+
+        // Don't insert a semicolon before `in` or `instanceof`, but do insert one
+        // before an identifier.
+        case 'i':
+            skip(lexer);
+
+            if (lexer->lookahead != 'n') {
+                return true;
+            }
+            skip(lexer);
+
+            if (!iswalpha(lexer->lookahead)) {
+                return false;
+            }
+
+            for (unsigned i = 0; i < 8; i++) {
+                if (lexer->lookahead != "stanceof"[i]) {
+                    return true;
+                }
+                skip(lexer);
+            }
+
+            if (!iswalpha(lexer->lookahead)) {
+                return false;
+            }
+            break;
+
+        default:
+            break;
+    }
+
+    return true;
+}
+
+static bool scan_ternary_qmark(TSLexer *lexer) {
+    for (;;) {
+        if (!iswspace(lexer->lookahead)) {
+            break;
+        }
+        skip(lexer);
+    }
+
+    if (lexer->lookahead == '?') {
+        advance(lexer);
+
+        if (lexer->lookahead == '?') {
+            return false;
+        }
+
+        lexer->mark_end(lexer);
+        lexer->result_symbol = TERNARY_QMARK;
+
+        if (lexer->lookahead == '.') {
+            advance(lexer);
+            if (iswdigit(lexer->lookahead)) {
+                return true;
+            }
+            return false;
+        }
+        return true;
+    }
+    return false;
+}
+
+static bool scan_html_comment(TSLexer *lexer) {
+    while (iswspace(lexer->lookahead) || lexer->lookahead == 0x2028 || lexer->lookahead == 0x2029) {
+        skip(lexer);
+    }
+
+    const char *comment_start = "<!--";
+    const char *comment_end = "-->";
+
+    if (lexer->lookahead == '<') {
+        for (unsigned i = 0; i < 4; i++) {
+            if (lexer->lookahead != comment_start[i]) {
+                return false;
+            }
+            advance(lexer);
+        }
+    } else if (lexer->lookahead == '-') {
+        for (unsigned i = 0; i < 3; i++) {
+            if (lexer->lookahead != comment_end[i]) {
+                return false;
+            }
+            advance(lexer);
+        }
+    } else {
+        return false;
+    }
+
+    while (lexer->lookahead != 0 && lexer->lookahead != '\n' && lexer->lookahead != 0x2028 &&
+           lexer->lookahead != 0x2029) {
+        advance(lexer);
+    }
+
+    lexer->result_symbol = HTML_COMMENT;
+    lexer->mark_end(lexer);
+
+    return true;
+}
+
+static bool scan_jsx_text(TSLexer *lexer) {
+    // saw_text will be true if we see any non-whitespace content, or any whitespace content that is not a newline and
+    // does not immediately follow a newline.
+    bool saw_text = false;
+    // at_newline will be true if we are currently at a newline, or if we are at whitespace that is not a newline but
+    // immediately follows a newline.
+    bool at_newline = false;
+
+    while (lexer->lookahead != 0 && lexer->lookahead != '<' && lexer->lookahead != '>' && lexer->lookahead != '{' &&
+           lexer->lookahead != '}' && lexer->lookahead != '&') {
+        bool is_wspace = iswspace(lexer->lookahead);
+        if (lexer->lookahead == '\n') {
+            at_newline = true;
+        } else {
+            // If at_newline is already true, and we see some whitespace, then it must stay true.
+            // Otherwise, it should be false.
+            //
+            // See the table below to determine the logic for computing `saw_text`.
+            //
+            // |------------------------------------|
+            // | at_newline | is_wspace | saw_text  |
+            // |------------|-----------|-----------|
+            // | false (0)  | false (0) | true  (1) |
+            // | false (0)  | true  (1) | true  (1) |
+            // | true  (1)  | false (0) | true  (1) |
+            // | true  (1)  | true  (1) | false (0) |
+            // |------------------------------------|
+
+            at_newline &= is_wspace;
+            if (!at_newline) {
+                saw_text = true;
+            }
+        }
+
+        advance(lexer);
+    }
+
+    lexer->result_symbol = JSX_TEXT;
+    return saw_text;
+}
+
+bool tree_sitter_javascript_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
+    if (valid_symbols[TEMPLATE_CHARS]) {
+        if (valid_symbols[AUTOMATIC_SEMICOLON]) {
+            return false;
+        }
+        return scan_template_chars(lexer);
+    }
+
+    if (valid_symbols[JSX_TEXT] && scan_jsx_text(lexer)) {
+        return true;
+    }
+
+    if (valid_symbols[AUTOMATIC_SEMICOLON]) {
+        bool scanned_comment = false;
+        bool ret = scan_automatic_semicolon(lexer, !valid_symbols[LOGICAL_OR], &scanned_comment);
+        if (!ret && !scanned_comment && valid_symbols[TERNARY_QMARK] && lexer->lookahead == '?') {
+            return scan_ternary_qmark(lexer);
+        }
+        return ret;
+    }
+
+    if (valid_symbols[TERNARY_QMARK]) {
+        return scan_ternary_qmark(lexer);
+    }
+
+    if (valid_symbols[HTML_COMMENT] && !valid_symbols[LOGICAL_OR] && !valid_symbols[ESCAPE_SEQUENCE] &&
+        !valid_symbols[REGEX_PATTERN]) {
+        return scan_html_comment(lexer);
+    }
+
+    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 +1,290 @@
+#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(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(default : 4101)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // TREE_SITTER_ARRAY_H_