Improve logging

lib/dic_chunk.py

@@ -44,6 +44,7 @@ def from_hunspell_dic(cls, dic_path: str, chunk_size: int, target_dir: str, samp
         Returns:
             A list of DicChunk objects, each representing a chunk of the dictionary file
         """
+        LOGGER.debug(f"Splitting dictionary file \"{dic_path}\" into chunks...")
         compounds = (True if 'compounds' in dic_path else False)
         with open(dic_path, 'r', encoding=LATIN_1_ENCODING) as dic_file:
             lines = dic_file.readlines()[1:]  # Skip the first line
@@ -65,6 +66,7 @@ def from_hunspell_dic(cls, dic_path: str, chunk_size: int, target_dir: str, samp
                 chunk_file.write(f"{len(chunk)}\n")
                 chunk_file.writelines(chunk)
             chunks.append(cls(chunk_path, compounds))
+        LOGGER.debug(f"Split into {len(chunks)} chunks.")
         return chunks
 
     def unmunch(self, aff_path: str, delete_tmp: bool = False) -> NamedTemporaryFile:

lib/languagetool_utils.py

@@ -46,6 +46,7 @@ def tokenise(self, unmunched_file: NamedTemporaryFile) -> NamedTemporaryFile:
         tokenisation_result = ShellCommand(tokenise_cmd).run_with_input(unmunched_str)
         tokenised_tmp.write(tokenisation_result)
         tokenised_tmp.flush()
+        LOGGER.debug(f"Done tokenising {unmunched_file.name}!")
         return tokenised_tmp
 
     def build_spelling_binary(self, tokenised_temps: List[NamedTemporaryFile]) -> None:
@@ -62,7 +63,7 @@ def build_spelling_binary(self, tokenised_temps: List[NamedTemporaryFile]) -> No
         Returns:
             None
         """
-        LOGGER.info(f"Building binary for {self.variant}...")
+        LOGGER.info(f"Building spelling binary for {self.variant}...")
         megatemp = NamedTemporaryFile(delete=self.delete_tmp, mode='w',
                                       encoding='utf-8')  # Open the file with UTF-8 encoding
         lines = set()
@@ -80,11 +81,12 @@ def build_spelling_binary(self, tokenised_temps: List[NamedTemporaryFile]) -> No
             f"-o {self.variant.dict()}"
         )
         ShellCommand(cmd_build).run()
-        LOGGER.info(f"Done compiling {self.variant} dictionary!")
+        LOGGER.info(f"Done compiling {self.variant} spelling dictionary!")
         self.variant.copy_spell_info()
         megatemp.close()
 
     def build_pos_binary(self) -> None:
+        LOGGER.info(f"Building part-of-speech binary for {self.variant}...")
         cmd_build = (
             f"java -cp {LT_JAR_PATH} "
             f"org.languagetool.tools.POSDictionaryBuilder "
@@ -93,9 +95,11 @@ def build_pos_binary(self) -> None:
             f"-o {self.variant.pos_dict_java_output_path()}"
         )
         ShellCommand(cmd_build).run()
+        LOGGER.info(f"Done compiling {self.variant} part-of-speech dictionary!")
         self.variant.copy_pos_info()
 
     def build_synth_binary(self) -> None:
+        LOGGER.info(f"Building synthesiser binary for {self.variant}...")
         cmd_build = (
             f"java -cp {LT_JAR_PATH} "
             f"org.languagetool.tools.SynthDictionaryBuilder "
@@ -104,5 +108,6 @@ def build_synth_binary(self) -> None:
             f"-o {self.variant.synth_dict_java_output_path()}"
         )
         ShellCommand(cmd_build).run()
+        LOGGER.info(f"Done compiling {self.variant} synthesiser dictionary!")
         self.variant.copy_synth_info()
         self.variant.rename_synth_tag_files()

lib/utils.py

@@ -1,5 +1,6 @@
 import codecs
 import shutil
+from datetime import timedelta
 from os import chdir, path
 from tempfile import NamedTemporaryFile
 from typing import Optional
@@ -39,3 +40,19 @@ def convert_to_utf8(tmp_file: NamedTemporaryFile, delete_tmp: bool = False) -> N
         shutil.copyfileobj(file, utf8_tmp)
     utf8_tmp.seek(0)
     return utf8_tmp
+
+
+def pretty_time_delta(time_delta: timedelta) -> str:
+    """Taken from https://gist.github.com/thatalextaylor/7408395 and tweaked slightly."""
+    seconds = int(time_delta.total_seconds())
+    days, seconds = divmod(seconds, 86400)
+    hours, seconds = divmod(seconds, 3600)
+    minutes, seconds = divmod(seconds, 60)
+    if days > 0:
+        return '%dd%dh%dmin%ds' % (days, hours, minutes, seconds)
+    elif hours > 0:
+        return '%dh%dmin%ds' % (hours, minutes, seconds)
+    elif minutes > 0:
+        return '%dmin%ds' % (minutes, seconds)
+    else:
+        return '%ds' % (seconds,)

scripts/build_spelling_dicts.py

@@ -9,7 +9,7 @@
 from lib.dic_chunk import DicChunk
 from lib.logger import LOGGER
 from lib.constants import SPELLING_DICT_DIR
-from lib.utils import compile_lt_dev, install_dictionaries, convert_to_utf8
+from lib.utils import compile_lt_dev, install_dictionaries, convert_to_utf8, pretty_time_delta
 from lib.variant import Variant, VARIANT_MAPPING
 from lib.languagetool_utils import LanguageToolUtils as LtUtils
 
@@ -69,7 +69,8 @@ def process_variant(variant: Variant, dic_chunk: DicChunk) -> tuple[Variant, Nam
 
 
 def main():
-    LOGGER.debug(f"started at {datetime.now().strftime('%r')}")
+    start_time = datetime.now()
+    LOGGER.debug(f"Started at {start_time.strftime('%r')}")
     LOGGER.debug(
         f"Options used:\n"
         f"TMP_DIR: {TMP_DIR}\n"
@@ -107,7 +108,9 @@ def main():
             file.close()
     if FORCE_INSTALL:
         install_dictionaries(CUSTOM_INSTALL_VERSION)
-    LOGGER.debug(f"finished at {datetime.now().strftime('%r')}")
+    end_time = datetime.now()
+    LOGGER.debug(f"Finished at {end_time.strftime('%r')}. "
+                 f"Total time elapsed: {pretty_time_delta(end_time - start_time)}.")
 
 
 if __name__ == "__main__":