philoch-bib-sdk 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

philoch_bib_sdk/adapters/tabular_data/read_journal_volume_number_index.py

@@ -0,0 +1,69 @@
+from functools import partial
+from typing import Callable, NamedTuple
+
+from philoch_bib_sdk.converters.plaintext.bibitem.bibkey_parser import hard_parse_bibkey, parse_bibkey
+from philoch_bib_sdk.logic.functions.journal_article_matcher import (
+    TJournalBibkeyIndex,
+    TReadIndex,
+)
+
+from aletk.ResultMonad import Err
+
+
+class ColumnNames(NamedTuple):
+    bibkey: str
+    journal: str
+    volume: str
+    number: str
+
+
+def _read_from_ods(
+    column_names: ColumnNames,
+    file_path: str,
+) -> TJournalBibkeyIndex:
+    """
+    Reads the specified columns from an ODS file and returns a TJournalBibkeyIndex dictionary.
+    Args:
+        column_names (ColumnNames): The names of the columns to read (journal, volume, number, bibkey).
+        file_path (str): The path to the ODS file.
+    Returns:
+        TJournalBibkeyIndex: A dictionary mapping (journal, volume, number) tuples to bibkey values.
+    """
+    import polars as pl
+
+    df = pl.read_ods(
+        source=file_path,
+        has_header=True,
+        columns=[column_names.journal, column_names.volume, column_names.number, column_names.bibkey],
+        schema_overrides={
+            column_names.journal: pl.Utf8,
+            column_names.volume: pl.Utf8,
+            column_names.number: pl.Utf8,
+            column_names.bibkey: pl.Utf8,
+        },
+    )
+
+    if df.is_empty():
+        raise ValueError(
+            f"Tabular data at '{file_path}' is empty or does not contain the expected columns: {column_names}"
+        )
+
+    bibkeys_parsed = (parse_bibkey(str(row[column_names.bibkey])) for row in df.to_dicts())
+
+    bibkey_errors = [bibkey for bibkey in bibkeys_parsed if isinstance(bibkey, Err)]
+
+    if bibkey_errors != []:
+        raise ValueError(
+            f"Failed to parse bibkeys in the ODS file at '{file_path}': {' --- '.join(str(bibkey_errors))}"
+        )
+
+    return {
+        (row[column_names.journal], row[column_names.volume], row[column_names.number]): hard_parse_bibkey(
+            row[column_names.bibkey]
+        )
+        for row in df.to_dicts()
+    }
+
+
+type THOFReadFromOds = Callable[[ColumnNames], TReadIndex]
+hof_read_from_ods: THOFReadFromOds = lambda column_names: partial(_read_from_ods, column_names)

philoch_bib_sdk/converters/plaintext/bibitem/bibkey_parser.py

@@ -142,3 +142,17 @@ def parse_bibkey(text: str) -> Ok[BibKeyAttr] | Err:
             error_type="BibkeyError",
             error_trace=f"{traceback.format_exc()}",
         )
+
+
+def hard_parse_bibkey(text: str) -> BibKeyAttr:
+    """
+    Hard parse a bibkey, without any error handling.
+    This is used for testing purposes only.
+    """
+
+    bibkey_parsed = parse_bibkey(text)
+
+    if isinstance(bibkey_parsed, Err):
+        raise ValueError(f"Could not hard parse '{text}' as bibkey: {bibkey_parsed.message}")
+
+    return bibkey_parsed.out

philoch_bib_sdk/logic/default_models.py

@@ -1,5 +1,7 @@
-from typing import Tuple, TypedDict, Unpack
+from typing import Tuple, TypedDict, Unpack, Literal
+from philoch_bib_sdk.logic.models import BibItem, PageAttr, KeywordsAttr, BibItemDateAttr, BibKeyAttr, Keyword
 
+from philoch_bib_sdk.logic.literals import TBasicPubState, TBibTeXEntryType, TEpoch, TLanguageID, TPubState
 from philoch_bib_sdk.logic.models import (
     Author,
     BaseNamedRenderable,
@@ -7,6 +9,7 @@ from philoch_bib_sdk.logic.models import (
     BibItem,
     BibStringAttr,
     Journal,
+    Keyword,
 )
 
 
@@ -118,3 +121,195 @@ def default_journal(**kwargs: Unpack[JournalArgs]) -> Journal | None:
         issn_electronic=kwargs.get("issn_electronic", ""),
         id=kwargs.get("id", None),
     )
+
+
+############
+# Support Args
+############
+
+
+class PageArgs(TypedDict, total=False):
+    start: str
+    end: str
+
+
+def default_page(**kwargs: Unpack[PageArgs]) -> PageAttr:
+    return PageAttr(
+        start=kwargs.get("start", ""),
+        end=kwargs.get("end", ""),
+    )
+
+
+class KeywordsArgs(TypedDict, total=False):
+    level_1: str
+    level_2: str
+    level_3: str
+
+
+def default_keywords(**kwargs: Unpack[KeywordsArgs]) -> KeywordsAttr:
+    return KeywordsAttr(
+        level_1=Keyword(name=kwargs.get("level_1", "")),
+        level_2=Keyword(name=kwargs.get("level_2", "")),
+        level_3=Keyword(name=kwargs.get("level_3", "")),
+    )
+
+
+class BibItemDateArgs(TypedDict, total=False):
+    year: int
+    year_part_2_hyphen: int | None
+    year_part_2_slash: int | None
+    month: int | None
+    day: int | None
+
+
+def default_bib_item_date(**kwargs: Unpack[BibItemDateArgs]) -> BibItemDateAttr:
+    return BibItemDateAttr(
+        year=kwargs.get("year", 0),
+        year_part_2_hyphen=kwargs.get("year_part_2_hyphen"),
+        year_part_2_slash=kwargs.get("year_part_2_slash"),
+        month=kwargs.get("month"),
+        day=kwargs.get("day"),
+    )
+
+
+def parse_date(date: BibItemDateArgs | Literal["no date"]) -> BibItemDateAttr | Literal["no date"]:
+    if isinstance(date, dict):
+        return default_bib_item_date(**date)
+    else:
+        return "no date"
+
+
+class BibKeyArgs(TypedDict, total=False):
+    first_author: str
+    other_authors: str
+    date: int | TBasicPubState
+    date_suffix: str
+
+
+def default_bib_key(**kwargs: Unpack[BibKeyArgs]) -> BibKeyAttr:
+    # Then pass to BibKeyAttr
+    return BibKeyAttr(
+        first_author=kwargs.get("first_author", ""),
+        other_authors=kwargs.get("other_authors", ""),
+        date=kwargs.get("date", ""),
+        date_suffix=kwargs.get("date_suffix", ""),
+    )
+
+
+############
+# BibItem Args
+############
+
+
+class BibItemArgs(TypedDict, total=False):
+    _to_do_general: str
+    _change_request: str
+    entry_type: TBibTeXEntryType
+    bibkey: BibKeyArgs
+    author: Tuple[AuthorArgs, ...]
+    editor: Tuple[AuthorArgs, ...]
+    options: Tuple[str, ...]
+    date: BibItemDateArgs | Literal["no date"]
+    pubstate: TPubState
+    title: BibStringArgs
+    booktitle: BibStringArgs
+    #    crossref: dict
+    journal: JournalArgs
+    volume: str
+    number: str
+    pages: Tuple[PageArgs, ...]
+    eid: str
+    series: BaseNamedRenderableArgs
+    address: BibStringArgs
+    institution: BibStringArgs
+    school: BibStringArgs
+    publisher: BibStringArgs
+    type: BibStringArgs
+    edition: int
+    note: BibStringArgs
+    issuetitle: BibStringArgs
+    _guesteditor: Tuple[AuthorArgs, ...]
+    _extra_note: BibStringArgs
+    urn: str
+    eprint: str
+    doi: str
+    url: str
+    _kws: KeywordsArgs
+    _epoch: TEpoch
+    _person: AuthorArgs
+    _comm_for_profile_bib: str
+    _langid: TLanguageID
+    _lang_der: str
+    _further_refs: Tuple[BibKeyArgs, ...]
+    _depends_on: Tuple[BibKeyArgs, ...]
+    _dltc_num: int
+    _spec_interest: str
+    _note_perso: str
+    _note_stock: str
+    _note_status: str
+    _num_inwork_coll: int
+    _num_inwork: str
+    _num_coll: int
+    _dltc_copyediting_note: str
+    _note_missing: str
+    _num_sort: int
+    id: int
+    _bib_info_source: str
+
+
+def default_bib_item(**kwargs: Unpack[BibItemArgs]) -> BibItem:
+    return BibItem(
+        to_do_general=kwargs.get("_to_do_general", ""),
+        change_request=kwargs.get("_change_request", ""),
+        entry_type=kwargs.get("entry_type", "UNKNOWN"),
+        bibkey=default_bib_key(**kwargs.get("bibkey", {})) if "bibkey" in kwargs else "",
+        author=tuple(default_author(**a) for a in kwargs.get("author", ())),
+        editor=tuple(default_author(**e) for e in kwargs.get("editor", ())),
+        options=kwargs.get("options", ()),
+        date=parse_date(kwargs.get("date", "no date")),
+        pubstate=kwargs.get("pubstate", ""),
+        title=default_bib_string(**kwargs.get("title", {})) if "title" in kwargs else "",
+        booktitle=default_bib_string(**kwargs.get("booktitle", {})) if "booktitle" in kwargs else "",
+        crossref="",  # Crossref is not defined in the provided context, so we leave it as an empty string
+        journal=default_journal(**kwargs.get("journal", {})) if "journal" in kwargs else None,
+        volume=kwargs.get("volume", ""),
+        number=kwargs.get("number", ""),
+        pages=tuple(default_page(**p) for p in kwargs.get("pages", ())),
+        eid=kwargs.get("eid", ""),
+        series=default_base_named_renderable(**kwargs.get("series", {})) if "series" in kwargs else "",
+        address=default_bib_string(**kwargs.get("address", {})) if "address" in kwargs else "",
+        institution=default_bib_string(**kwargs.get("institution", {})) if "institution" in kwargs else "",
+        school=default_bib_string(**kwargs.get("school", {})) if "school" in kwargs else "",
+        publisher=default_bib_string(**kwargs.get("publisher", {})) if "publisher" in kwargs else "",
+        type=default_bib_string(**kwargs.get("type", {})) if "type" in kwargs else "",
+        edition=kwargs.get("edition"),
+        note=default_bib_string(**kwargs.get("note", {})) if "note" in kwargs else "",
+        issuetitle=default_bib_string(**kwargs.get("issuetitle", {})) if "issuetitle" in kwargs else "",
+        guesteditor=tuple(default_author(**a) for a in kwargs.get("_guesteditor", ())),
+        extra_note=default_bib_string(**kwargs.get("_extra_note", {})) if "_extra_note" in kwargs else "",
+        urn=kwargs.get("urn", ""),
+        eprint=kwargs.get("eprint", ""),
+        doi=kwargs.get("doi", ""),
+        url=kwargs.get("url", ""),
+        kws=default_keywords(**kwargs.get("_kws", {})) if "_kws" in kwargs else "",
+        epoch=kwargs.get("_epoch", ""),
+        person=default_author(**kwargs.get("_person", {})) if "_person" in kwargs else "",
+        comm_for_profile_bib=kwargs.get("_comm_for_profile_bib", ""),
+        langid=kwargs.get("_langid", ""),
+        lang_der=kwargs.get("_lang_der", ""),
+        further_refs=tuple(default_bib_key(**b) for b in kwargs.get("_further_refs", ())),
+        depends_on=tuple(default_bib_key(**b) for b in kwargs.get("_depends_on", ())),
+        dltc_num=kwargs.get("_dltc_num"),
+        spec_interest=kwargs.get("_spec_interest", ""),
+        note_perso=kwargs.get("_note_perso", ""),
+        note_stock=kwargs.get("_note_stock", ""),
+        note_status=kwargs.get("_note_status", ""),
+        num_inwork_coll=kwargs.get("_num_inwork_coll"),
+        num_inwork=kwargs.get("_num_inwork", ""),
+        num_coll=kwargs.get("_num_coll"),
+        dltc_copyediting_note=kwargs.get("_dltc_copyediting_note", ""),
+        note_missing=kwargs.get("_note_missing", ""),
+        num_sort=kwargs.get("_num_sort"),
+        id=kwargs.get("id"),
+        bib_info_source=kwargs.get("_bib_info_source", ""),
+    )

philoch_bib_sdk/logic/functions/journal_article_matcher.py

@@ -0,0 +1,42 @@
+from typing import Callable, Dict, Tuple
+from philoch_bib_sdk.converters.plaintext.journal.formatter import format_journal
+from philoch_bib_sdk.logic.models import BibItem, BibKeyAttr
+
+
+type TJournalName = str
+
+type TVolume = str
+
+type TNumber = str
+
+type TBibkey = str
+
+
+type TJournalBibkeyIndex = Dict[
+    Tuple[TJournalName, TVolume, TNumber], BibKeyAttr
+]  # (journal, volume, number)  # bibkey
+
+
+def get_bibkey_by_journal_volume_number(index: TJournalBibkeyIndex, subject: BibItem) -> BibKeyAttr:
+    """
+    Simple lookup of a Bibitem on an index for its bibkey, via the combination (journal_name, volume, number). Fails if any of the three fields are missing.
+    """
+
+    journal = format_journal(subject.journal, bibstring_type="latex")
+    volume = subject.volume
+    number = subject.number
+
+    if any((journal == "", volume == "", number == "")):
+        raise ValueError(
+            f"Expected subject bibitem journal with non-empty journal, volume, and number. Found [[ journal: {journal}; volume: {volume}; number: {number} ]] instead."
+        )
+
+    return index[(journal, volume, number)]
+
+
+type TReadIndex = Callable[
+    [
+        str,  # path to the index file
+    ],
+    TJournalBibkeyIndex,
+]

{philoch_bib_sdk-0.1.3.dist-info → philoch_bib_sdk-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: philoch-bib-sdk
-Version: 0.1.3
+Version: 0.1.5
 Summary: Standard development kit for the Philosophie Bibliography project
 License: MIT
 Author: Luis Alejandro Bordo García
@@ -13,6 +13,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: aletk (>=0.1.6,<0.2.0)
 Requires-Dist: attrs (>=25.3.0,<26.0.0)
+Requires-Dist: polars (>=1.32.3,<2.0.0)
 Description-Content-Type: text/markdown
 
 # Philosophie.ch Bibliography SDK

{philoch_bib_sdk-0.1.3.dist-info → philoch_bib_sdk-0.1.5.dist-info}/RECORD

@@ -1,10 +1,11 @@
 philoch_bib_sdk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+philoch_bib_sdk/adapters/tabular_data/read_journal_volume_number_index.py,sha256=6ocGGl9nZXqyHkPxJp5GH1NIfb-BUMTYqr84QwZOPd8,2210
 philoch_bib_sdk/converters/latex.py,sha256=LuAKLrClECuBeaDQYJc7tIJECEV4h0kt0VE_ssv3s0o,236
 philoch_bib_sdk/converters/plaintext/author/formatter.py,sha256=hsqKUyNhIZeqisnEQU43DokAfEfG78rgQ8POTjYnToM,965
 philoch_bib_sdk/converters/plaintext/author/parser.py,sha256=LL12mtgN59eJCv551c6s7YfMTjfJAJqm-jRQkdntmIg,2514
 philoch_bib_sdk/converters/plaintext/bib_string_formatter.py,sha256=5Z97u5GryHUgZcPhWE41thgWCB4wYu22pZ9et6nakmw,329
 philoch_bib_sdk/converters/plaintext/bibitem/bibkey_formatter.py,sha256=YivsY0gblKJdC4yKYZ3tvWmKIvFXW4iNht9zhz8oFUs,565
-philoch_bib_sdk/converters/plaintext/bibitem/bibkey_parser.py,sha256=lmcDD-NN0hiAF_uKRUcucTBELd_F9q_qjbW9Df7srwY,4624
+philoch_bib_sdk/converters/plaintext/bibitem/bibkey_parser.py,sha256=TKHFQ9QeZ2Jgm3sFCjTqz_PDfous0amvz3DB0AJA51E,4991
 philoch_bib_sdk/converters/plaintext/bibitem/date_formatter.py,sha256=G2mbaJidDg8avKBbro1rVcEznPC92XVTDQ4fSdmvhJo,1480
 philoch_bib_sdk/converters/plaintext/bibitem/date_parser.py,sha256=3ZYGhhGqILzrvnwOvG4NPAjErLwVva0dfsN0B9eFomg,2242
 philoch_bib_sdk/converters/plaintext/bibitem/formatter.py,sha256=EjSwHYAPn0YRjeLGK_rCi26Wtug6X5x5DFEKPjStn30,6298
@@ -14,13 +15,14 @@ philoch_bib_sdk/converters/plaintext/bibitem/parser.py,sha256=B8xF3OKr6R4-FwsV8i
 philoch_bib_sdk/converters/plaintext/journal/formatter.py,sha256=o5ikU-aNFr6cxgzD0rBCjymHLpGrD6RGvNE8V2sX52s,599
 philoch_bib_sdk/converters/plaintext/journal/parser.py,sha256=kT1YHwc9Am82WHRhaSWXaCeKitPn9QLWIbmIe8T1of4,1092
 philoch_bib_sdk/converters/plaintext/shared/renderable_formatter.py,sha256=oS5u8RJpkRXaDTmauVqZi-uuXsyG-UQZMK2pgzSk-qo,686
-philoch_bib_sdk/logic/default_models.py,sha256=UnPmtPyNfqkKaTuhWLi5hiP1FCPJRnLXqsjH1gYrQic,3368
+philoch_bib_sdk/logic/default_models.py,sha256=cHHKSFmNR29qBxQkPwelQ09sx66isHlAIr1PiIHAvH4,10467
 philoch_bib_sdk/logic/functions/comparator.py,sha256=4G5EUEVf8v6URt1v1Fqk1pjqni6fxUs_Goh4EQ4RBJY,4034
+philoch_bib_sdk/logic/functions/journal_article_matcher.py,sha256=IcnTv07Gk68M1LGB0Y9Z2DZsLYsWRzJCeL_c1r29bqg,1219
 philoch_bib_sdk/logic/literals.py,sha256=_9poyFdSqbMWNg686xaexvkZTIrpCbQqPNTCVi0PlFc,1573
 philoch_bib_sdk/logic/models.py,sha256=xHCQWFq_rEcX967icALD4oOQjM8AlLKLzXQ8SP-YNis,8681
 philoch_bib_sdk/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-philoch_bib_sdk-0.1.3.dist-info/LICENSE,sha256=nplGobji9gkYmJxDBbBz2SKjZY27SUaqhqKkpUB-C30,1070
-philoch_bib_sdk-0.1.3.dist-info/METADATA,sha256=o2nbm6-lqZ_1hrs9SBLFLWircDKtyWRKvhuYoNFF2mI,776
-philoch_bib_sdk-0.1.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-philoch_bib_sdk-0.1.3.dist-info/entry_points.txt,sha256=5PDcoKK00cdaL0CabioRUz08ZJeXLa94Ca-C0umGPTU,46
-philoch_bib_sdk-0.1.3.dist-info/RECORD,,
+philoch_bib_sdk-0.1.5.dist-info/LICENSE,sha256=nplGobji9gkYmJxDBbBz2SKjZY27SUaqhqKkpUB-C30,1070
+philoch_bib_sdk-0.1.5.dist-info/METADATA,sha256=wGBNDCmurQsZbrDFiO9PrTHUfp0B3dLeLOLre7Io6Ns,816
+philoch_bib_sdk-0.1.5.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+philoch_bib_sdk-0.1.5.dist-info/entry_points.txt,sha256=5PDcoKK00cdaL0CabioRUz08ZJeXLa94Ca-C0umGPTU,46
+philoch_bib_sdk-0.1.5.dist-info/RECORD,,