debug

include/interpreter_tree.hpp

@@ -526,6 +526,7 @@ struct AnnotatedType : public Node {
 };
 
 using TypeParameter = std::variant<
+  std::unique_ptr<TypeExpression>,
   std::unique_ptr<ParametrizedType>,
   std::unique_ptr<Expression>>;
 

include/parse_tree.hpp

@@ -5,6 +5,7 @@
 // for clangd
 #include "tree_sitter/api.h"
 
+extern "C" const TSLanguage* tree_sitter_LANG();
 
 namespace parser {
 
@@ -12,31 +13,76 @@ class ParseTree {
 public:
   class Node {
   public:
-    std::string GetType();
-    std::pair<size_t, size_t> GetStartPoint();
-    std::pair<size_t, size_t> GetEndPoint();
-    std::string GetAsSExpression();
+    Node() = default;
+    Node(const TSNode &node, const std::string* source) : node_(node), source_(source) {}
 
-    std::string GetValue(); // from source
+    std::string GetType() {
+        return ts_node_type(node_);
+    }
 
-    bool IsNull();
-    bool IsNamed();
-    bool IsMissing();
-    bool IsExtra(); // comments, etc.
-    bool HasError();
+    std::pair<size_t, size_t> GetStartPoint() {
+        TSPoint point = ts_node_start_point(node_);
+        return {point.row, point.column};
+    }
 
-    Node NthChild(size_t n);
-    size_t ChildCount();
+    std::pair<size_t, size_t> GetEndPoint() {
+        TSPoint point = ts_node_end_point(node_);
+        return {point.row, point.column};
+    }
 
-    Node NthNamedChild(size_t n);
-    size_t NamedChildCount();
+    std::string GetAsSExpression() {
+      return ts_node_string(node_);
+    }
 
-    Node ChildByFieldName(const std::string& name);
+    std::string GetValue() { // from source
+      size_t start = ts_node_start_byte(node_);
+      size_t end = ts_node_end_byte(node_);
+      return source_->substr(start, end - start); // TODO check
+    }
+
+    bool IsNull() {
+      return ts_node_is_null(node_);
+    }
+
+    bool IsNamed() {
+      return ts_node_is_named(node_);
+    }
+
+    bool IsMissing() {
+      return ts_node_is_missing(node_);
+    }
+
+    bool IsExtra() { // comments, etc.
+      return ts_node_is_extra(node_);
+    }
+
+    bool HasError() {
+      return ts_node_has_error(node_);
+    }
+
+    Node NthChild(size_t n) {
+      return Node(ts_node_child(node_, n), source_);
+    }
+    size_t ChildCount() {
+      return ts_node_child_count(node_);
+    }
+
+    Node NthNamedChild(size_t n) {
+      return Node(ts_node_named_child(node_, n), source_);
+    }
+    size_t NamedChildCount() {
+      return ts_node_named_child_count(node_);
+    }
+
+    Node ChildByFieldName(const std::string& name) {
+      return Node(ts_node_child_by_field_name(node_, name.c_str(), name.size()), source_);
+    }
 
     // ?? use field id instaed of name ??
     // ?? node equality check needed ??
   private:
     TSNode node_;
+    const std::string* source_ = nullptr;
   };
   class Cursor { // ?? needed ??
   public:
@@ -54,12 +100,24 @@ public:
     TSTreeCursor cursor_;
   };
 
-  ParseTree(const std::string& input);
+  ParseTree(const std::string& source) : source_(source) {
+    TSParser* parser = ts_parser_new();
+    ts_parser_set_language(parser, tree_sitter_LANG());
+
+    tree_ = ts_parser_parse_string(
+      parser,
+      NULL,
+      source_.c_str(),
+      source_.size());
+  }
+
+  Node GetRoot() const {
+    return Node(ts_tree_root_node(tree_), &source_);
+  }
 
-  Node GetRoot() const;
 private:
   TSTree* tree_;
-  std::string source; // for token value extraction
+  std::string source_; // for token value extraction
 };
 
 } // namespace parser

include/parser.h

@@ -0,0 +1,224 @@
+#ifndef TREE_SITTER_PARSER_H_
+#define TREE_SITTER_PARSER_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#define ts_builtin_sym_error ((TSSymbol)-1)
+#define ts_builtin_sym_end 0
+#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
+
+typedef uint16_t TSStateId;
+
+#ifndef TREE_SITTER_API_H_
+typedef uint16_t TSSymbol;
+typedef uint16_t TSFieldId;
+typedef struct TSLanguage TSLanguage;
+#endif
+
+typedef struct {
+  TSFieldId field_id;
+  uint8_t child_index;
+  bool inherited;
+} TSFieldMapEntry;
+
+typedef struct {
+  uint16_t index;
+  uint16_t length;
+} TSFieldMapSlice;
+
+typedef struct {
+  bool visible;
+  bool named;
+  bool supertype;
+} TSSymbolMetadata;
+
+typedef struct TSLexer TSLexer;
+
+struct TSLexer {
+  int32_t lookahead;
+  TSSymbol result_symbol;
+  void (*advance)(TSLexer *, bool);
+  void (*mark_end)(TSLexer *);
+  uint32_t (*get_column)(TSLexer *);
+  bool (*is_at_included_range_start)(const TSLexer *);
+  bool (*eof)(const TSLexer *);
+};
+
+typedef enum {
+  TSParseActionTypeShift,
+  TSParseActionTypeReduce,
+  TSParseActionTypeAccept,
+  TSParseActionTypeRecover,
+} TSParseActionType;
+
+typedef union {
+  struct {
+    uint8_t type;
+    TSStateId state;
+    bool extra;
+    bool repetition;
+  } shift;
+  struct {
+    uint8_t type;
+    uint8_t child_count;
+    TSSymbol symbol;
+    int16_t dynamic_precedence;
+    uint16_t production_id;
+  } reduce;
+  uint8_t type;
+} TSParseAction;
+
+typedef struct {
+  uint16_t lex_state;
+  uint16_t external_lex_state;
+} TSLexMode;
+
+typedef union {
+  TSParseAction action;
+  struct {
+    uint8_t count;
+    bool reusable;
+  } entry;
+} TSParseActionEntry;
+
+struct TSLanguage {
+  uint32_t version;
+  uint32_t symbol_count;
+  uint32_t alias_count;
+  uint32_t token_count;
+  uint32_t external_token_count;
+  uint32_t state_count;
+  uint32_t large_state_count;
+  uint32_t production_id_count;
+  uint32_t field_count;
+  uint16_t max_alias_sequence_length;
+  const uint16_t *parse_table;
+  const uint16_t *small_parse_table;
+  const uint32_t *small_parse_table_map;
+  const TSParseActionEntry *parse_actions;
+  const char * const *symbol_names;
+  const char * const *field_names;
+  const TSFieldMapSlice *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;
+  bool (*lex_fn)(TSLexer *, TSStateId);
+  bool (*keyword_lex_fn)(TSLexer *, TSStateId);
+  TSSymbol keyword_capture_token;
+  struct {
+    const bool *states;
+    const TSSymbol *symbol_map;
+    void *(*create)(void);
+    void (*destroy)(void *);
+    bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist);
+    unsigned (*serialize)(void *, char *);
+    void (*deserialize)(void *, const char *, unsigned);
+  } external_scanner;
+  const TSStateId *primary_state_ids;
+};
+
+/*
+ *  Lexer Macros
+ */
+
+#define START_LEXER()           \
+  bool result = false;          \
+  bool skip = false;            \
+  bool eof = false;             \
+  int32_t lookahead;            \
+  goto start;                   \
+  next_state:                   \
+  lexer->advance(lexer, skip);  \
+  start:                        \
+  skip = false;                 \
+  lookahead = lexer->lookahead;
+
+#define ADVANCE(state_value) \
+  {                          \
+    state = state_value;     \
+    goto next_state;         \
+  }
+
+#define SKIP(state_value) \
+  {                       \
+    skip = true;          \
+    state = state_value;  \
+    goto next_state;      \
+  }
+
+#define ACCEPT_TOKEN(symbol_value)     \
+  result = true;                       \
+  lexer->result_symbol = symbol_value; \
+  lexer->mark_end(lexer);
+
+#define END_STATE() return result;
+
+/*
+ *  Parse Table Macros
+ */
+
+#define SMALL_STATE(id) id - LARGE_STATE_COUNT
+
+#define STATE(id) id
+
+#define ACTIONS(id) id
+
+#define SHIFT(state_value)            \
+  {{                                  \
+    .shift = {                        \
+      .type = TSParseActionTypeShift, \
+      .state = state_value            \
+    }                                 \
+  }}
+
+#define SHIFT_REPEAT(state_value)     \
+  {{                                  \
+    .shift = {                        \
+      .type = TSParseActionTypeShift, \
+      .state = state_value,           \
+      .repetition = true              \
+    }                                 \
+  }}
+
+#define SHIFT_EXTRA()                 \
+  {{                                  \
+    .shift = {                        \
+      .type = TSParseActionTypeShift, \
+      .extra = true                   \
+    }                                 \
+  }}
+
+#define REDUCE(symbol_val, child_count_val, ...) \
+  {{                                             \
+    .reduce = {                                  \
+      .type = TSParseActionTypeReduce,           \
+      .symbol = symbol_val,                      \
+      .child_count = child_count_val,            \
+      __VA_ARGS__                                \
+    },                                           \
+  }}
+
+#define RECOVER()                    \
+  {{                                 \
+    .type = TSParseActionTypeRecover \
+  }}
+
+#define ACCEPT_INPUT()              \
+  {{                                \
+    .type = TSParseActionTypeAccept \
+  }}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // TREE_SITTER_PARSER_H_