philoch-bib-sdk 0.1.3__tar.gz → 0.1.5__tar.gz

{philoch_bib_sdk-0.1.3 → philoch_bib_sdk-0.1.5}/PKG-INFO

@@ -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-0.1.5/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-0.1.3 → philoch_bib_sdk-0.1.5}/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-0.1.5/philoch_bib_sdk/logic/default_models.py

@@ -0,0 +1,315 @@
+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,
+    BaseRenderable,
+    BibItem,
+    BibStringAttr,
+    Journal,
+    Keyword,
+)
+
+
+class BibStringArgs(TypedDict, total=False):
+    latex: str
+    unicode: str
+    simplified: str
+
+
+def default_bib_string(**kwargs: Unpack[BibStringArgs]) -> BibStringAttr:
+    """
+    Create a default BibString object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
+    """
+    return BibStringAttr(
+        latex=kwargs.get("latex", ""),
+        unicode=kwargs.get("unicode", ""),
+        simplified=kwargs.get("simplified", ""),
+    )
+
+
+############
+# Base Renderables
+############
+
+
+class BaseRenderableArgs(TypedDict, total=False):
+    text: BibStringArgs
+    id: int | None
+
+
+def default_base_renderable(**kwargs: Unpack[BaseRenderableArgs]) -> BaseRenderable:
+    """
+    Create a default BaseRenderable object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
+    """
+    return BaseRenderable(
+        text=default_bib_string(**kwargs.get("text", {})),
+        id=kwargs.get("id", None),
+    )
+
+
+class BaseNamedRenderableArgs(TypedDict, total=False):
+    name: BibStringArgs
+    id: int | None
+
+
+def default_base_named_renderable(**kwargs: Unpack[BaseNamedRenderableArgs]) -> BaseNamedRenderable:
+    """
+    Create a default BaseNamedRenderable object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
+    """
+    return BaseNamedRenderable(
+        name=default_bib_string(**kwargs.get("name", {})),
+        id=kwargs.get("id", None),
+    )
+
+
+############
+# Author
+############
+
+
+class AuthorArgs(TypedDict, total=False):
+    given_name: BibStringArgs
+    family_name: BibStringArgs
+    mononym: BibStringArgs
+    shorthand: BibStringArgs
+    famous_name: BibStringArgs
+    publications: Tuple[BibItem, ...]
+    id: int | None
+
+
+def default_author(**kwargs: Unpack[AuthorArgs]) -> Author:
+    """
+    Create a default Author object, given a dictionary with any (or None) of its attributes. Defaults to empty strings and an empty tuple for publications if not provided.
+    """
+
+    return Author(
+        given_name=default_bib_string(**kwargs.get("given_name", {})),
+        family_name=default_bib_string(**kwargs.get("family_name", {})),
+        mononym=default_bib_string(**kwargs.get("mononym", {})),
+        shorthand=default_bib_string(**kwargs.get("shorthand", {})),
+        famous_name=default_bib_string(**kwargs.get("famous_name", {})),
+        publications=kwargs.get("publications", ()),
+        id=kwargs.get("id", None),
+    )
+
+
+############
+# Journal
+############
+
+
+class JournalArgs(TypedDict, total=False):
+    name: BibStringArgs
+    issn_print: str
+    issn_electronic: str
+    id: int | None
+
+
+def default_journal(**kwargs: Unpack[JournalArgs]) -> Journal | None:
+    """
+    Create a default Journal object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
+    """
+    if kwargs == {}:
+        return None
+
+    return Journal(
+        name=default_bib_string(**kwargs.get("name", {})),
+        issn_print=kwargs.get("issn_print", ""),
+        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-0.1.5/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 → philoch_bib_sdk-0.1.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "philoch-bib-sdk"
-version = "0.1.3"
+version = "0.1.5"
 description = "Standard development kit for the Philosophie Bibliography project"
 authors = [
     {name = "Luis Alejandro Bordo García", email = "luis.bordo@philosophie.ch"}
@@ -19,6 +19,7 @@ build-backend = "poetry.core.masonry.api"
 [tool.poetry.dependencies]
 aletk = "^0.1.6"
 attrs = "^25.3.0"
+polars = "^1.32.3"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.5"
@@ -27,6 +28,8 @@ black = {extras = ["jupyter"], version = "^25.1.0"}
 jupyter = "^1.1.1"
 pytest-env = "^1.1.5"
 autoflake = "^2.3.1"
+odswriter = "^0.4.0"
+fastexcel = "^0.14.0"
 
 [tool.poetry.group.experimental.dependencies]
 cytoolz = "^1.0.1"
@@ -52,6 +55,7 @@ env = [
 [[tool.mypy.overrides]]
 module = [
     "cytoolz",
+    "odswriter",
 ]
 ignore_missing_imports = true
 

philoch_bib_sdk-0.1.3/philoch_bib_sdk/logic/default_models.py

@@ -1,120 +0,0 @@
-from typing import Tuple, TypedDict, Unpack
-
-from philoch_bib_sdk.logic.models import (
-    Author,
-    BaseNamedRenderable,
-    BaseRenderable,
-    BibItem,
-    BibStringAttr,
-    Journal,
-)
-
-
-class BibStringArgs(TypedDict, total=False):
-    latex: str
-    unicode: str
-    simplified: str
-
-
-def default_bib_string(**kwargs: Unpack[BibStringArgs]) -> BibStringAttr:
-    """
-    Create a default BibString object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
-    """
-    return BibStringAttr(
-        latex=kwargs.get("latex", ""),
-        unicode=kwargs.get("unicode", ""),
-        simplified=kwargs.get("simplified", ""),
-    )
-
-
-############
-# Base Renderables
-############
-
-
-class BaseRenderableArgs(TypedDict, total=False):
-    text: BibStringArgs
-    id: int | None
-
-
-def default_base_renderable(**kwargs: Unpack[BaseRenderableArgs]) -> BaseRenderable:
-    """
-    Create a default BaseRenderable object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
-    """
-    return BaseRenderable(
-        text=default_bib_string(**kwargs.get("text", {})),
-        id=kwargs.get("id", None),
-    )
-
-
-class BaseNamedRenderableArgs(TypedDict, total=False):
-    name: BibStringArgs
-    id: int | None
-
-
-def default_base_named_renderable(**kwargs: Unpack[BaseNamedRenderableArgs]) -> BaseNamedRenderable:
-    """
-    Create a default BaseNamedRenderable object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
-    """
-    return BaseNamedRenderable(
-        name=default_bib_string(**kwargs.get("name", {})),
-        id=kwargs.get("id", None),
-    )
-
-
-############
-# Author
-############
-
-
-class AuthorArgs(TypedDict, total=False):
-    given_name: BibStringArgs
-    family_name: BibStringArgs
-    mononym: BibStringArgs
-    shorthand: BibStringArgs
-    famous_name: BibStringArgs
-    publications: Tuple[BibItem, ...]
-    id: int | None
-
-
-def default_author(**kwargs: Unpack[AuthorArgs]) -> Author:
-    """
-    Create a default Author object, given a dictionary with any (or None) of its attributes. Defaults to empty strings and an empty tuple for publications if not provided.
-    """
-
-    return Author(
-        given_name=default_bib_string(**kwargs.get("given_name", {})),
-        family_name=default_bib_string(**kwargs.get("family_name", {})),
-        mononym=default_bib_string(**kwargs.get("mononym", {})),
-        shorthand=default_bib_string(**kwargs.get("shorthand", {})),
-        famous_name=default_bib_string(**kwargs.get("famous_name", {})),
-        publications=kwargs.get("publications", ()),
-        id=kwargs.get("id", None),
-    )
-
-
-############
-# Journal
-############
-
-
-class JournalArgs(TypedDict, total=False):
-    name: BibStringArgs
-    issn_print: str
-    issn_electronic: str
-    id: int | None
-
-
-def default_journal(**kwargs: Unpack[JournalArgs]) -> Journal | None:
-    """
-    Create a default Journal object, given a dictionary with any (or None) of its attributes. Defaults to empty strings if not provided.
-    """
-    if kwargs == {}:
-        return None
-
-    return Journal(
-        name=default_bib_string(**kwargs.get("name", {})),
-        issn_print=kwargs.get("issn_print", ""),
-        issn_electronic=kwargs.get("issn_electronic", ""),
-        id=kwargs.get("id", None),
-    )