Revert "common : introduce composable PEG parser combinators for chat parsing and new jinja template engine (ikawrakow#1369)"

This reverts commit ab1d740.

Author: Nexesenex

README.md

@@ -222,47 +222,4 @@ Contributions in form of pull requests, issue submissions (bug reports, feature
 
 ## License
 
-- [subprocess.h](https://github.com/sheredom/subprocess.h) - Single-header process launching solution for C and C++ - Public domain
-- [server](example/server/README.md)
-- [GBNF grammars](grammars/README.md)
-
-#### Development documentation
-
-- [How to build](docs/build.md)
-- [Running on Docker](docs/docker.md)
-- [Performance troubleshooting](docs/development/token_generation_performance_tips.md)
-- [GGML tips & tricks](https://github.com/ggml-org/llama.cpp/wiki/GGML-Tips-&-Tricks)
-
-#### Seminal papers and background on the models
-
-If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:
-- LLaMA:
-    - [Introducing LLaMA: A foundational, 65-billion-parameter large language model](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/)
-    - [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
-- GPT-3
-    - [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165)
-- GPT-3.5 / InstructGPT / ChatGPT:
-    - [Aligning language models to follow instructions](https://openai.com/research/instruction-following)
-    - [Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
-
-## Completions
-Command-line completion is available for some environments.
-
-#### Bash Completion
-```bash
-$ build/bin/llama-cli --completion-bash > ~/.llama-completion.bash
-$ source ~/.llama-completion.bash
-```
-Optionally this can be added to your `.bashrc` or `.bash_profile` to load it
-automatically. For example:
-```console
-$ echo "source ~/.llama-completion.bash" >> ~/.bashrc
-```
-
-## Dependencies
-
-- [yhirose/cpp-httplib](https://github.com/yhirose/cpp-httplib) - Single-header HTTP server, used by `llama-server` - MIT license
-- [stb-image](https://github.com/nothings/stb) - Single-header image format decoder, used by multimodal subsystem - Public domain
-- [nlohmann/json](https://github.com/nlohmann/json) - Single-header JSON library, used by various tools/examples - MIT License
-- [miniaudio.h](https://github.com/mackron/miniaudio) - Single-header audio format decoder, used by multimodal subsystem - Public domain
-- [subprocess.h](https://github.com/sheredom/subprocess.h) - Single-header process launching solution for C and C++ - Public domain
+MIT

ci/run.sh

@@ -141,7 +141,7 @@ function gg_run_ctest_release {
     (time make -j                                            ) 2>&1 | tee -a $OUT/${ci}-make.log
 
     if [ -z ${GG_BUILD_LOW_PERF} ]; then
-        (time ctest --output-on-failure -L 'main|python' ) 2>&1 | tee -a $OUT/${ci}-ctest.log
+        (time ctest --output-on-failure -L main ) 2>&1 | tee -a $OUT/${ci}-ctest.log
     else
         (time ctest --output-on-failure -L main -E test-opt ) 2>&1 | tee -a $OUT/${ci}-ctest.log
     fi

common/CMakeLists.txt

@@ -58,8 +58,6 @@ add_library(${TARGET} STATIC
     chat-parser.h
     chat-parser-xml-toolcall.h
     chat-parser-xml-toolcall.cpp
-	chat-peg-parser.cpp
-    chat-peg-parser.h
     common.cpp
     sampling.h
     sampling.cpp
@@ -77,27 +75,11 @@ add_library(${TARGET} STATIC
     ngram-cache.h
     ngram-map.cpp
     ngram-map.h
-	peg-parser.cpp
-    peg-parser.h
 	speculative.cpp
-    unicode.cpp
-    unicode.h
     ngram-mod.cpp
     ngram-mod.h
     regex-partial.cpp
     regex-partial.h
-    jinja/lexer.cpp
-    jinja/lexer.h
-    jinja/parser.cpp
-    jinja/parser.h
-    jinja/runtime.cpp
-    jinja/runtime.h
-    jinja/value.cpp
-    jinja/value.h
-    jinja/string.cpp
-    jinja/string.h
-    jinja/caps.cpp
-    jinja/caps.h
     )
 
 if (BUILD_SHARED_LIBS)

common/chat-parser-xml-toolcall.cpp

@@ -842,7 +842,7 @@ inline void parse_msg_with_xml_tool_calls(common_chat_msg_parser & builder, cons
         }
 
         // remove potential partial suffix
-        if (builder.pos() == builder.input().size() && builder.is_partial()) {
+        if (builder.pos() == builder.input().size()) {
             if (unclosed_reasoning_content.empty()) {
                 rstrip(content);
                 trim_potential_partial_word(content);

common/chat-parser.cpp

@@ -1,8 +1,6 @@
 #include "chat-parser.h"
-#include "chat-peg-parser.h"
 #include "common.h"
 #include "log.h"
-#include "peg-parser.h"
 #include "regex-partial.h"
 
 #include <algorithm>
@@ -551,7 +549,7 @@ std::optional<common_chat_msg_parser::consume_json_result> common_chat_msg_parse
         if (is_arguments_path({})) {
             // Entire JSON is the arguments and was parsed fully.
             return consume_json_result {
-                partial->json.dump(/* indent */ -1, /* indent_char */ ' ', /* ensure_ascii */ true),
+                partial->json.dump(),
                 /* .is_partial = */ false,
             };
         }
@@ -563,7 +561,7 @@ std::optional<common_chat_msg_parser::consume_json_result> common_chat_msg_parse
     std::vector<std::string> path;
     std::function<json(const json &)> remove_unsupported_healings_and_dump_args = [&](const json & j) -> json {
         if (is_arguments_path(path)) {
-            auto arguments = j.dump(/* indent */ -1, /* indent_char */ ' ', /* ensure_ascii */ true);
+            auto arguments = j.dump();
             if (is_partial() && !partial->healing_marker.marker.empty()) {
                 auto idx = arguments.find(partial->healing_marker.json_dump_marker);
                 if (idx != std::string::npos) {
@@ -898,19 +896,19 @@ static void common_chat_parse_minimax_m2(common_chat_msg_parser & builder) {
 
 static void common_chat_parse_qwen3_coder_xml(common_chat_msg_parser & builder) {
     static const xml_tool_call_format form = ([]() {
-        xml_tool_call_format form{};
+        xml_tool_call_format form {};
         form.scope_start = "<tool_call>";
-        form.tool_start = "<function=";
-        form.tool_sep = ">";
-        form.key_start = "<parameter=";
+        form.tool_start  = "<function=";
+        form.tool_sep    = ">";
+        form.key_start   = "<parameter=";
         form.key_val_sep = ">";
-        form.val_end = "</parameter>";
-        form.tool_end = "</function>";
-        form.scope_end = "</tool_call>";
+        form.val_end     = "</parameter>";
+        form.tool_end    = "</function>";
+        form.scope_end   = "</tool_call>";
         form.trim_raw_argval = true;
         return form;
-        })();
-        builder.consume_reasoning_with_xml_tool_calls(form);
+    })();
+    builder.consume_reasoning_with_xml_tool_calls(form);
 }
 
 static void common_chat_parse_kimi_k2(common_chat_msg_parser & builder) {
@@ -1510,11 +1508,6 @@ static void common_chat_parse(common_chat_msg_parser & builder) {
 }
 
 common_chat_msg common_chat_parse(const std::string & input, bool is_partial, const common_chat_syntax & syntax) {
-    if (syntax.format == COMMON_CHAT_FORMAT_PEG_SIMPLE ||
-        syntax.format == COMMON_CHAT_FORMAT_PEG_NATIVE ||
-        syntax.format == COMMON_CHAT_FORMAT_PEG_CONSTRUCTED) {
-        return common_chat_peg_parse(syntax.parser, input, is_partial, syntax);
-    }
     common_chat_msg_parser builder(input, is_partial, syntax);
     try {
         common_chat_parse(builder);
@@ -1528,40 +1521,7 @@ common_chat_msg common_chat_parse(const std::string & input, bool is_partial, co
     }
     auto msg = builder.result();
     if (!is_partial) {
-        LOG_DBG("Parsed message: %s\n", common_chat_msgs_to_json_oaicompat({msg}).at(0).dump().c_str());
-    }
-    return msg;
-}
-
-common_chat_msg common_chat_peg_parse(const common_peg_arena & parser, const std::string & input, bool is_partial, const common_chat_syntax & syntax) {
-    if (parser.empty()) {
-        throw std::runtime_error("Failed to parse due to missing parser definition.");
-    }
-
-    LOG_DBG("Parsing input with format %s: %s\n", common_chat_format_name(syntax.format), input.c_str());
-
-    common_peg_parse_context ctx(input, is_partial);
-    auto result = parser.parse(ctx);
-    if (result.fail()) {
-        throw std::runtime_error(std::string("Failed to parse input at pos ") + std::to_string(result.end));
-    }
-
-    common_chat_msg msg;
-    msg.role = "assistant";
-
-    if (syntax.format == COMMON_CHAT_FORMAT_PEG_NATIVE) {
-        auto mapper = common_chat_peg_native_mapper(msg);
-        mapper.from_ast(ctx.ast, result);
-    } else if (syntax.format == COMMON_CHAT_FORMAT_PEG_CONSTRUCTED) {
-        auto mapper = common_chat_peg_constructed_mapper(msg);
-        mapper.from_ast(ctx.ast, result);
-    } else {
-        // Generic mapper
-        auto mapper = common_chat_peg_mapper(msg);
-        mapper.from_ast(ctx.ast, result);
-    }
-    if (!is_partial) {
-        LOG_DBG("Parsed message: %s\n", common_chat_msgs_to_json_oaicompat({msg}).at(0).dump().c_str());
+        LOG_DBG("Parsed message: %s\n", common_chat_msgs_to_json_oaicompat<json>({msg}).at(0).dump().c_str());
     }
     return msg;
 }