common : implement parser combinators for chat parsing [WIP]

common/CMakeLists.txt

@@ -52,6 +52,8 @@ add_library(${TARGET} STATIC
     chat-parser.h
     chat-parser-xml-toolcall.h
     chat-parser-xml-toolcall.cpp
+    chat-peg-parser.cpp
+    chat-peg-parser.h
     chat.cpp
     chat.h
     common.cpp
@@ -69,12 +71,16 @@ add_library(${TARGET} STATIC
     log.h
     ngram-cache.cpp
     ngram-cache.h
+    peg-parser.cpp
+    peg-parser.h
     regex-partial.cpp
     regex-partial.h
     sampling.cpp
     sampling.h
     speculative.cpp
     speculative.h
+    unicode.cpp
+    unicode.h
     )
 
 if (BUILD_SHARED_LIBS)

common/chat-peg-parser.cpp

@@ -0,0 +1,111 @@
+#include "chat-peg-parser.h"
+
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+
+static std::string_view trim_trailing_space(std::string_view sv) {
+    while (!sv.empty() && std::isspace(static_cast<unsigned char>(sv.back()))) {
+        sv.remove_suffix(1);
+    }
+    return sv;
+}
+
+void common_chat_peg_mapper::from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & result) {
+    arena.visit(result, [this](const common_peg_ast_node & node) {
+        map(node);
+    });
+}
+
+void common_chat_peg_mapper::map(const common_peg_ast_node & node) {
+    bool is_reasoning = node.tag == common_chat_peg_builder::REASONING;
+    bool is_content = node.tag == common_chat_peg_builder::CONTENT;
+
+    if (is_reasoning) {
+        result.reasoning_content = std::string(trim_trailing_space(node.text));
+    }
+
+    if (is_content) {
+        result.content = std::string(trim_trailing_space(node.text));
+    }
+}
+
+void common_chat_peg_native_mapper::map(const common_peg_ast_node & node) {
+    common_chat_peg_mapper::map(node);
+
+    bool is_tool_open = node.tag == common_chat_peg_native_builder::TOOL_OPEN;
+    bool is_tool_name = node.tag == common_chat_peg_native_builder::TOOL_NAME;
+    bool is_tool_id = node.tag == common_chat_peg_native_builder::TOOL_ID;
+    bool is_tool_args = node.tag == common_chat_peg_native_builder::TOOL_ARGS;
+
+    if (is_tool_open) {
+        result.tool_calls.emplace_back();
+        current_tool = &result.tool_calls.back();
+    }
+
+    if (is_tool_id && current_tool) {
+        current_tool->id = std::string(node.text);
+    }
+
+    if (is_tool_name && current_tool) {
+        current_tool->name = std::string(node.text);
+    }
+
+    if (is_tool_args && current_tool) {
+        current_tool->arguments = std::string(node.text);
+    }
+}
+
+void common_chat_peg_constructed_mapper::map(const common_peg_ast_node & node) {
+    common_chat_peg_mapper::map(node);
+
+    bool is_tool_name = node.tag == common_chat_peg_constructed_builder::TOOL_NAME;
+    bool is_tool_close = node.tag == common_chat_peg_constructed_builder::TOOL_CLOSE;
+    bool is_arg_open = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_OPEN;
+    bool is_arg_close = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_CLOSE;
+    bool is_arg_name = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_NAME;
+    bool is_arg_string = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_STRING_VALUE;
+    bool is_arg_json = node.tag == common_chat_peg_constructed_builder::TOOL_ARG_JSON_VALUE;
+
+    if (is_tool_name) {
+        result.tool_calls.emplace_back();
+        current_tool = &result.tool_calls.back();
+        arg_count = 0;
+
+        current_tool->name = std::string(node.text);
+        current_tool->arguments = "{";
+    }
+
+    if (is_arg_open) {
+        needs_closing_quote = false;
+    }
+
+    if (is_arg_name && current_tool) {
+        if (arg_count > 0) {
+            current_tool->arguments += ",";
+        }
+        current_tool->arguments += json(node.text).dump() + ":";
+        ++arg_count;
+    }
+
+    if (is_arg_string && current_tool) {
+        // Serialize to JSON, but exclude the end quote
+        std::string dumped = json(node.text).dump();
+        current_tool->arguments += dumped.substr(0, dumped.size() - 1);
+        needs_closing_quote = true;
+    }
+
+    if (is_arg_close && current_tool) {
+        if (needs_closing_quote) {
+            current_tool->arguments += "\"";
+        }
+    }
+
+    if (is_arg_json && current_tool) {
+        current_tool->arguments += std::string(node.text);
+    }
+
+    if (is_tool_close && current_tool) {
+        current_tool->arguments += "}";
+    }
+}

common/chat-peg-parser.h

@@ -0,0 +1,105 @@
+#pragma once
+
+#include "chat.h"
+#include "peg-parser.h"
+
+class common_chat_peg_builder : public common_peg_parser_builder {
+  public:
+    static constexpr const char * REASONING_BLOCK = "reasoning-block";
+    static constexpr const char * REASONING = "reasoning";
+    static constexpr const char * CONTENT = "content";
+
+    common_peg_parser reasoning_block(const common_peg_parser & p) { return tag(REASONING_BLOCK, p); }
+    common_peg_parser reasoning(const common_peg_parser & p) { return tag(REASONING, p); }
+    common_peg_parser content(const common_peg_parser & p) { return tag(CONTENT, p); }
+};
+
+inline common_peg_arena build_chat_peg_parser(const std::function<common_peg_parser(common_chat_peg_builder & builder)> & fn) {
+    common_chat_peg_builder builder;
+    builder.set_root(fn(builder));
+    return builder.build();
+}
+
+class common_chat_peg_mapper {
+  public:
+    common_chat_msg & result;
+
+    common_chat_peg_mapper(common_chat_msg & msg) : result(msg) {}
+
+    virtual void from_ast(const common_peg_ast_arena & arena, const common_peg_parse_result & result);
+    virtual void map(const common_peg_ast_node & node);
+};
+
+class common_chat_peg_native_builder : public common_chat_peg_builder {
+  public:
+    static constexpr const char * TOOL = "tool";
+    static constexpr const char * TOOL_OPEN = "tool-open";
+    static constexpr const char * TOOL_CLOSE = "tool-close";
+    static constexpr const char * TOOL_ID = "tool-id";
+    static constexpr const char * TOOL_NAME = "tool-name";
+    static constexpr const char * TOOL_ARGS = "tool-args";
+
+    common_peg_parser tool(const common_peg_parser & p) { return tag(TOOL, p); }
+    common_peg_parser tool_open(const common_peg_parser & p) { return atomic(tag(TOOL_OPEN, p)); }
+    common_peg_parser tool_close(const common_peg_parser & p) { return atomic(tag(TOOL_CLOSE, p)); }
+    common_peg_parser tool_id(const common_peg_parser & p) { return atomic(tag(TOOL_ID, p)); }
+    common_peg_parser tool_name(const common_peg_parser & p) { return atomic(tag(TOOL_NAME, p)); }
+    common_peg_parser tool_args(const common_peg_parser & p) { return tag(TOOL_ARGS, p); }
+};
+
+class common_chat_peg_native_mapper : public common_chat_peg_mapper {
+    common_chat_tool_call * current_tool;
+
+  public:
+    common_chat_peg_native_mapper(common_chat_msg & msg) : common_chat_peg_mapper(msg) {}
+
+    void map(const common_peg_ast_node & node) override;
+};
+
+inline common_peg_arena build_chat_peg_native_parser(const std::function<common_peg_parser(common_chat_peg_native_builder & builder)> & fn) {
+    common_chat_peg_native_builder builder;
+    builder.set_root(fn(builder));
+    return builder.build();
+}
+
+class common_chat_peg_constructed_builder : public common_chat_peg_builder {
+  public:
+    static constexpr const char * TOOL = "tool";
+    static constexpr const char * TOOL_OPEN = "tool-open";
+    static constexpr const char * TOOL_CLOSE = "tool-close";
+    static constexpr const char * TOOL_NAME = "tool-name";
+    static constexpr const char * TOOL_ARG = "tool-arg";
+    static constexpr const char * TOOL_ARG_OPEN = "tool-arg-open";
+    static constexpr const char * TOOL_ARG_CLOSE = "tool-arg-close";
+    static constexpr const char * TOOL_ARG_NAME = "tool-arg-name";
+    static constexpr const char * TOOL_ARG_STRING_VALUE = "tool-arg-string-value";
+    static constexpr const char * TOOL_ARG_JSON_VALUE = "tool-arg-json-value";
+
+    common_peg_parser tool(const common_peg_parser & p) { return tag(TOOL, p); }
+    common_peg_parser tool_open(const common_peg_parser & p) { return atomic(tag(TOOL_OPEN, p)); }
+    common_peg_parser tool_close(const common_peg_parser & p) { return atomic(tag(TOOL_CLOSE, p)); }
+    common_peg_parser tool_name(const common_peg_parser & p) { return atomic(tag(TOOL_NAME, p)); }
+    common_peg_parser tool_arg(const common_peg_parser & p) { return tag(TOOL_ARG, p); }
+    common_peg_parser tool_arg_open(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_OPEN, p)); }
+    common_peg_parser tool_arg_close(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_CLOSE, p)); }
+    common_peg_parser tool_arg_name(const common_peg_parser & p) { return atomic(tag(TOOL_ARG_NAME, p)); }
+    common_peg_parser tool_arg_string_value(const common_peg_parser & p) { return tag(TOOL_ARG_STRING_VALUE, p); }
+    common_peg_parser tool_arg_json_value(const common_peg_parser & p) { return tag(TOOL_ARG_JSON_VALUE, p); }
+};
+
+class common_chat_peg_constructed_mapper : public common_chat_peg_mapper {
+    common_chat_tool_call * current_tool;
+    int arg_count = 0;
+    bool needs_closing_quote = false;
+
+  public:
+    common_chat_peg_constructed_mapper(common_chat_msg & msg) : common_chat_peg_mapper(msg) {}
+
+    void map(const common_peg_ast_node & node) override;
+};
+
+inline common_peg_arena build_chat_peg_constructed_parser(const std::function<common_peg_parser(common_chat_peg_constructed_builder & builder)> & fn) {
+    common_chat_peg_constructed_builder builder;
+    builder.set_root(fn(builder));
+    return builder.build();
+}