convert.py : add python logging instead of print() (#6511)

* convert.py: add python logging instead of print()

* convert.py: verbose flag takes priority over dump flag log suppression

* convert.py: named instance logging

* convert.py: use explicit logger id string

* convert.py: convert extra print() to named logger

* convert.py: sys.stderr.write --> logger.error

* *.py: Convert all python scripts to use logging module

* requirements.txt: remove extra line

* flake8: update flake8 ignore and exclude to match ci settings

* gh-actions: add flake8-no-print to flake8 lint step

* pre-commit: add flake8-no-print to flake8 and also update pre-commit version

* convert-hf-to-gguf.py: print() to logger conversion

* *.py: logging basiconfig refactor to use conditional expression

* *.py: removed commented out logging

* fixup! *.py: logging basiconfig refactor to use conditional expression

* constant.py: logger.error then exit should be a raise exception instead

* *.py: Convert logger error and sys.exit() into a raise exception (for atypical error)

* gguf-convert-endian.py: refactor convert_byteorder() to use tqdm progressbar

* verify-checksum-model.py: This is the result of the program, it should be printed to stdout.

* compare-llama-bench.py: add blank line for readability during missing repo response

* reader.py: read_gguf_file() use print() over logging

* convert.py: warning goes to stderr and won't hurt the dump output

* gguf-dump.py: dump_metadata() should print to stdout

* convert-hf-to-gguf.py: print --> logger.debug or ValueError()

* verify-checksum-models.py: use print() for printing table

* *.py: refactor logging.basicConfig()

* gguf-py/gguf/*.py: use __name__ as logger name

Since they will be imported and not run directly.

* python-lint.yml: use .flake8 file instead

* constants.py: logger no longer required

* convert-hf-to-gguf.py: add additional logging

* convert-hf-to-gguf.py: print() --> logger

* *.py: fix flake8 warnings

* revert changes to convert-hf-to-gguf.py for get_name()

* convert-hf-to-gguf-update.py: use triple quoted f-string instead

* *.py: accidentally corrected the wrong line

* *.py: add compilade warning suggestions and style fixes

1 files changed, 13 insertions, 29 deletions

diff --git a/gguf-py/gguf/vocab.py b/gguf-py/gguf/vocab.py
index 378eaeca..c97a78f3 100644
--- a/gguf-py/gguf/vocab.py
+++ b/gguf-py/gguf/vocab.py
@@ -1,13 +1,15 @@
 from __future__ import annotations
 
+import logging
 import json
 import os
-import sys
 from pathlib import Path
 from typing import Any, Callable
 
 from .gguf_writer import GGUFWriter
 
+logger = logging.getLogger(__name__)
+
 
 class SpecialVocab:
     merges: list[str]
@@ -40,38 +42,29 @@ class SpecialVocab:
     def add_to_gguf(self, gw: GGUFWriter, quiet: bool = False) -> None:
         if self.merges:
             if not quiet:
-                print(f'gguf: Adding {len(self.merges)} merge(s).')
+                logger.info(f'Adding {len(self.merges)} merge(s).')
             gw.add_token_merges(self.merges)
         elif self.load_merges:
-            print(
-                'gguf: WARNING: Adding merges requested but no merges found, output may be non-functional.',
-                file = sys.stderr,
-            )
+            logger.warning('Adding merges requested but no merges found, output may be non-functional.')
         for typ, tokid in self.special_token_ids.items():
             id_handler: Callable[[int], None] | None = getattr(gw, f'add_{typ}_token_id', None)
             if id_handler is None:
-                print(
-                    f'gguf: WARNING: No handler for special token type {typ} with id {tokid} - skipping',
-                    file = sys.stderr,
-                )
+                logger.warning(f'No handler for special token type {typ} with id {tokid} - skipping')
                 continue
             if not quiet:
-                print(f'gguf: Setting special token type {typ} to {tokid}')
+                logger.info(f'Setting special token type {typ} to {tokid}')
             id_handler(tokid)
         for typ, value in self.add_special_token.items():
             add_handler: Callable[[bool], None] | None = getattr(gw, f'add_add_{typ}_token', None)
             if add_handler is None:
-                print(
-                    f'gguf: WARNING: No handler for add_{typ}_token with value {value} - skipping',
-                    file = sys.stderr,
-                )
+                logger.warning(f'No handler for add_{typ}_token with value {value} - skipping')
                 continue
             if not quiet:
-                print(f'gguf: Setting add_{typ}_token to {value}')
+                logger.info(f'Setting add_{typ}_token to {value}')
             add_handler(value)
         if self.chat_template is not None:
             if not quiet:
-                print(f'gguf: Setting chat_template to {self.chat_template}')
+                logger.info(f'Setting chat_template to {self.chat_template}')
             gw.add_chat_template(self.chat_template)
 
     def _load(self, path: Path) -> None:
@@ -99,10 +92,7 @@ class SpecialVocab:
                     continue
                 parts = line.split(None, 3)
                 if len(parts) != 2:
-                    print(
-                        f'gguf: WARNING: {merges_file.name}: Line {line_num}: Entry malformed, ignoring',
-                        file = sys.stderr,
-                    )
+                    logger.warning(f'{merges_file.name}: Line {line_num}: Entry malformed, ignoring')
                     continue
                 merges.append(f'{parts[0]} {parts[1]}')
         self.merges = merges
@@ -118,10 +108,7 @@ class SpecialVocab:
                 return
             self.special_token_ids[typ] = tid
             return
-        print(
-            f'gguf: WARNING: Special token type {typ}, id {tid} out of range, must be under {self.n_vocab} - skipping',
-            file = sys.stderr,
-        )
+        logger.warning(f'Special token type {typ}, id {tid} out of range, must be under {self.n_vocab} - skipping')
 
     def _try_load_from_tokenizer_json(self, path: Path) -> bool:
         tokenizer_file = path / 'tokenizer.json'
@@ -144,10 +131,7 @@ class SpecialVocab:
         if chat_template is None or isinstance(chat_template, (str, list)):
             self.chat_template = chat_template
         else:
-            print(
-                f'gguf: WARNING: Bad type for chat_template field in {tokenizer_config_file!r} - ignoring',
-                file = sys.stderr
-            )
+            logger.warning(f'Bad type for chat_template field in {tokenizer_config_file!r} - ignoring')
         for typ in self.special_token_types:
             add_entry = tokenizer_config.get(f'add_{typ}_token')
             if isinstance(add_entry, bool):