feat: support book chapter

tests/cases.py

@@ -5,7 +5,7 @@
 import textwrap
 from dataclasses import dataclass
 
-from wenxian.reference import Author, Reference
+from wenxian.reference import Author, BibtexType, Reference
 
 
 @dataclass
@@ -453,4 +453,25 @@ class ReferenceCase:
                          applications in drug development and beyond.},
             }""").strip(),
     ),
+    # chapter
+    ReferenceCase(
+        reference=Reference(
+            author=[Author(first="James Patton", last="Jones")],
+            title="PBS: Portable Batch System",
+            year=2001,
+            pages=(369, 390),
+            doi="10.7551/mitpress/1556.003.0021",
+            journal="Beowulf Cluster Computing with Linux",
+            type=BibtexType.inbook,
+        ),
+        expected_bibtex=textwrap.dedent(r"""
+            @Inbook{Jones_BeowulfClustComputLinux_2001_p369,
+                author =   {James Patton Jones},
+                title =    {{PBS: Portable Batch System}},
+                year =     2001,
+                pages =    {369--390},
+                doi =      {10.7551/mitpress/1556.003.0021},
+                booktitle ={Beowulf Cluster Computing with Linux},
+            }""").strip(),
+    ),
 ]

wenxian/feeder/crossref.py

@@ -6,7 +6,7 @@
 
 from wenxian.feeder.feeder import Feeder
 from wenxian.feeder.session import SESSION
-from wenxian.reference import Author, Reference
+from wenxian.reference import Author, BibtexType, Reference
 
 
 class Crossref(Feeder):
@@ -64,8 +64,50 @@ def from_doi(self, doi: str) -> Reference | None:
             # while not documented, the journal might be HTML escaped, e.g., Journal of Materials Science & Technology
             # https://api.crossref.org/works/10.1016/j.jmst.2023.09.059
             journal = html.unescape(journal)
+        elif m.get("container-title"):
+            journal = m["container-title"][0]
+            journal = html.unescape(journal)
         else:
             journal = None
+        # journal-article
+        # journal-issue
+        # journal-volume
+        # journal
+        # proceedings-article
+        # proceedings
+        # dataset
+        # component
+        # report
+        # report-series
+        # standard
+        # standard-series
+        # edited-book
+        # monograph
+        # reference-book
+        # book
+        # book-series
+        # book-set
+        # book-chapter
+        # book-section
+        # book-part
+        # book-track
+        # reference-entry
+        # dissertation
+        # posted-content
+        # peer-review
+        # other
+        cr_type = m.get("type")
+        if cr_type in (
+            "book-series",
+            "book-set",
+            "book-chapter",
+            "book-section",
+            "book-part",
+            "book-track",
+        ):
+            ref_type = BibtexType.inbook
+        else:
+            ref_type = BibtexType.article
         return Reference(
             author=author,
             title=title,
@@ -76,4 +118,5 @@ def from_doi(self, doi: str) -> Reference | None:
             pages=self._pages(page),
             annote=abstract,
             doi=doi,
+            type=ref_type,
         )

wenxian/reference.py

@@ -5,6 +5,7 @@
 import re
 import textwrap
 from dataclasses import dataclass
+from enum import IntEnum
 
 import unidecode
 from pyiso4.ltwa import Abbreviate
@@ -52,6 +53,25 @@ def __str__(self) -> str:
         return f"{self.first} {self.last}"
 
 
+class BibtexType(IntEnum):
+    """BibTeX entry types."""
+
+    article = 0
+    book = 1
+    booklet = 2
+    conference = 3
+    inbook = 4
+    incollection = 5
+    inproceedings = 6
+    manual = 7
+    mastersthesis = 8
+    misc = 9
+    phdthesis = 10
+    proceedings = 11
+    techreport = 12
+    unpublished = 13
+
+
 @dataclass
 class Reference:
     """A reference to a scholarly article."""
@@ -65,6 +85,7 @@ class Reference:
     pages: tuple[int] | tuple[int, int] | str | None = None
     annote: str | None = None
     doi: str | None = None
+    type: BibtexType = BibtexType.article
 
     @property
     def journal_abbr(self) -> str | None:
@@ -153,7 +174,11 @@ def bibtex(self) -> str:
             "doi": self.doi,
             "abstract": self.annote,
         }
-        start = f"@Article{{{self.key},"
+        if self.type in (BibtexType.inbook,):
+            data.pop("journal")
+            # usually book title should not use abbr
+            data["booktitle"] = self.journal
+        start = f"@{self.type.name.capitalize()}{{{self.key},"
         end = "}\n"
         items = [start]
         for key, value in data.items():
@@ -202,6 +227,7 @@ def __or__(self, other: Reference | None) -> Reference:
             pages=self.pages or other.pages,
             annote=self.annote or other.annote,
             doi=self.doi or other.doi,
+            type=self.type or other.type,
         )
 
     def is_empty(self) -> bool: