Skip to content

Refactor parser to use string entry_types #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
s-heppner merged 1 commit into from
May 4, 2025
+57 −86
Merged

Refactor parser to use string entry_types #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions bibtex_linter/default_rules.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
from typing import List, Set

from bibtex_linter.parser import BibTeXEntry, EntryType
from bibtex_linter.parser import BibTeXEntry
from bibtex_linter.verification import (
linter_rule,
check_required_fields,
check_omitted_fields,
)


@linter_rule(entry_type=EntryType.ARTICLE)
@linter_rule(entry_type="article")
def check_article(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.ARTICLE` are there and that there are no fields present, that would
Expand All @@ -34,7 +34,7 @@ def check_article(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.CONFERENCE)
@linter_rule(entry_type="conference")
def check_conference(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.CONFERENCE` are there and that there are no fields present, that would
Expand Down Expand Up @@ -64,7 +64,7 @@ def check_conference(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.ONLINE)
@linter_rule(entry_type="online")
def check_online(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.ONLINE` are there and that there are no fields present, that would
Expand Down Expand Up @@ -95,7 +95,7 @@ def check_online(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.BOOK)
@linter_rule(entry_type="book")
def check_book(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.BOOK` are there and that there are no fields present, that would
Expand Down Expand Up @@ -123,7 +123,7 @@ def check_book(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.IN_BOOK)
@linter_rule(entry_type="inbook")
def check_in_book(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.IN_BOOK` are there and that there are no fields present, that would
Expand Down Expand Up @@ -153,7 +153,7 @@ def check_in_book(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.IN_COLLECTION)
@linter_rule(entry_type="incollection")
def check_in_collection(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.IN_COLLECTION` are there and that there are no fields present, that
Expand All @@ -180,7 +180,7 @@ def check_in_collection(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.STANDARD)
@linter_rule(entry_type="standard")
def check_standard(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.STANDARD` are there and that there are no fields present, that would
Expand Down Expand Up @@ -212,7 +212,7 @@ def check_standard(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.TECH_REPORT)
@linter_rule(entry_type="techreport")
def check_tech_report(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.TECH_REPORT` are there and that there are no fields present, that
Expand Down Expand Up @@ -242,7 +242,7 @@ def check_tech_report(entry: BibTeXEntry) -> List[str]:
return invariant_violations


@linter_rule(entry_type=EntryType.MISC)
@linter_rule(entry_type="misc")
def check_misc(entry: BibTeXEntry) -> List[str]:
"""
Check that the required fields for `EntryType.MISC` are there and that there are no fields present, that would
Expand Down
2 changes: 1 addition & 1 deletion bibtex_linter/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ def main() -> None:
total_number_of_violations += len(violations)
if violations:
had_violations = True
print(f"\nEntry '{entry.name}' of type '{entry.entry_type.name}' failed verification:")
print(f"\nEntry '{entry.name}' of type '{entry.entry_type}' failed verification:")
print(" ❌ Invariant Violations:")
for issue in violations:
print(f" - {issue}")
Expand Down
61 changes: 16 additions & 45 deletions bibtex_linter/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,55 +4,19 @@
import re


class EntryType(enum.Enum):
"""
A collection of entry types that the LaTeX `IEEEtran` offers. Note that these only include what I
need at the moment. The full list can be found at:
https://ctan.net/macros/latex/contrib/IEEEtran/bibtex/IEEEtran_bst_HOWTO.pdf
"""
ARTICLE = "ARTICLE" # A typical journal article
CONFERENCE = "CONFERENCE" # A typical conference paper. Alias to: `IN_PROCEEDINGS`
ONLINE = "ONLINE" # A reference on the internet. Alias to: `ELECTRONIC`
BOOK = "BOOK" # Referencing a whole book
IN_BOOK = "IN_BOOK" # Referencing a part of a book (chapters or pages)
IN_COLLECTION = "IN_COLLECTION" # Referencing a part of a book that has its own name
STANDARD = "STANDARD" # Used for proposed or formally published standards
TECH_REPORT = "TECH_REPORT" # Used for technical reports, or reports about standards. Compare to `STANDARD`!
MISC = "MISC" # Anything else that does not fit the above

@classmethod
def from_string(cls, s: str) -> 'EntryType':
"""
Get the `EntryType` from the string. Can deal with common aliases.

:raises: KeyError, if the given string does not correspond to one of the entry types
"""
s = s.upper()
str_to_entry_type_map: Dict[str, "EntryType"] = {
"ARTICLE": EntryType.ARTICLE,
"CONFERENCE": EntryType.CONFERENCE,
"INPROCEEDINGS": EntryType.CONFERENCE,

"BOOK": EntryType.BOOK,
"INBOOK": EntryType.IN_BOOK,
"INCOLLECTION": EntryType.IN_COLLECTION,
"STANDARD": EntryType.STANDARD,
"TECHREPORT": EntryType.TECH_REPORT,

"ONLINE": EntryType.ONLINE,
"ELECTRONIC": EntryType.ONLINE,

"MISC": EntryType.MISC,
}
return str_to_entry_type_map[s]
RESOLVE_ENTRY_TYPE_ALIAS: Dict[str, str] = {
"inproceedings": "conference",
"electronic": "online",
}


@dataclasses.dataclass
class BibTeXEntry:
"""
An entry in a BibTeX file

:ivar entry_type: Type of the entry (e.g. `@misc`). See `EntryType` for details
:ivar entry_type: Type of the entry (e.g. `@misc`). We always assume that the `entry_type` is in small letters only,
and we transform some common `entry_type` aliases to their "canonical" form (e.g. the name I prefer to use).
:ivar name: Name or ID of the entry. So basically what is here: `@misc{Name_or_ID,`
:ivar fields: Fields of the entry, as a Dict mapping the field key (e.g. `author`) to its cleaned up value.

Expand All @@ -72,14 +36,21 @@ class BibTeXEntry:
will be parsed to: `{"note": "This value\nspans multiple\nlines"}`. For the implementation details, check out
the `BibTeXEntry._parse_field_value` static method.
"""
entry_type: EntryType
entry_type: str
name: str
fields: Dict[str, str]

@classmethod
def from_string(cls, entry_string: str) -> "BibTeXEntry":
entry_type_string: str = entry_string.split("{")[0].lstrip("@")
entry_type = EntryType.from_string(entry_type_string)
"""
Parse a `BibTeXEntry` from a string.
"""
# First, we find and canonicalize the `entry_type`
entry_type_string: str = entry_string.split("{")[0].lstrip("@").lower()
if RESOLVE_ENTRY_TYPE_ALIAS.get(entry_type_string):
entry_type: str = RESOLVE_ENTRY_TYPE_ALIAS[entry_type_string]
else:
entry_type = entry_type_string

name: str = entry_string.split("{")[1].split(",")[0]
raw_fields = cls._split_fields(entry_string)
Expand Down
4 changes: 2 additions & 2 deletions bibtex_linter/verification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"""
from typing import Callable, TypeVar, List, Optional, Set

from bibtex_linter.parser import BibTeXEntry, EntryType
from bibtex_linter.parser import BibTeXEntry

# The dynamic list of known rules.
# This list gets updated when a method with the `@linter_rule` decorator gets imported.
Expand All @@ -17,7 +17,7 @@
LINTER_RULE_TYPE = TypeVar("LINTER_RULE_TYPE", bound=Callable[[BibTeXEntry], List[str]])


def linter_rule(entry_type: Optional[EntryType] = None) -> Callable[[LINTER_RULE_TYPE], LINTER_RULE_TYPE]:
def linter_rule(entry_type: Optional[str] = None) -> Callable[[LINTER_RULE_TYPE], LINTER_RULE_TYPE]:
"""
Decorator to mark a method defines rules to be checked by the linter for a specific entry type.

Expand Down
56 changes: 28 additions & 28 deletions test/test_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import os
from typing import Dict, List

from bibtex_linter.parser import EntryType, BibTeXEntry, split_entries, parse_bibtex_file
from bibtex_linter.parser import BibTeXEntry, split_entries, parse_bibtex_file


class TestBibTeXEntry(unittest.TestCase):
Expand Down Expand Up @@ -245,15 +245,15 @@ def test_parse_all_entries(self) -> None:
self.assertEqual(17, len(entries))

expected_types = {
EntryType.ARTICLE: 1,
EntryType.CONFERENCE: 1,
EntryType.ONLINE: 1,
EntryType.TECH_REPORT: 1,
EntryType.BOOK: 1,
EntryType.MISC: 9,
EntryType.STANDARD: 1,
EntryType.IN_BOOK: 1,
EntryType.IN_COLLECTION: 1,
"article": 1,
"conference": 1,
"online": 1,
"techreport": 1,
"book": 1,
"misc": 9,
"standard": 1,
"inbook": 1,
"incollection": 1,
}

for entry_type, expected_count in expected_types.items():
Expand All @@ -262,121 +262,121 @@ def test_parse_all_entries(self) -> None:
self.assertEqual(expected_count, actual_count)

def test_entry_fields_and_values(self) -> None:
expected_entries: List[Dict[str, EntryType | Dict[str, str]]] = [
expected_entries: List[Dict[str, str | Dict[str, str]]] = [
{
"type": EntryType.ARTICLE,
"type": "article",
"fields": {
"author": "Tests basic article",
"title": "Standard field format",
"year": "2020"
}
},
{
"type": EntryType.CONFERENCE,
"type": "conference",
"fields": {
"author": "Should map to CONFERENCE",
"title": "Using alias INPROCEEDINGS",
"year": "2021"
}
},
{
"type": EntryType.ONLINE,
"type": "online",
"fields": {
"author": "Should map to ONLINE",
"url": "https://example.com"
}
},
{
"type": EntryType.TECH_REPORT,
"type": "techreport",
"fields": {
"author": "Should map to TECH_REPORT",
"title": "Tech report via alias"
}
},
{
"type": EntryType.BOOK,
"type": "book",
"fields": {
"author": "Extra spaces around field and value",
"title": "Trimmed Title",
"year": "2023"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"note": "This has nested braces inside",
"comment": "But only outermost braces should be stripped"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"author": "Double brace test",
"title": "Another level of nesting"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"author": "Quoted Author",
"title": "Simple quoted title"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"note": "This value\nspans multiple\nlines"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"howpublished": r"\url{https://wrapped-url.com}"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"title": r"\LaTeX command in value"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"author": "Trailing Comma",
"title": "Should be OK"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"author": "No Trailing Comma"
}
},
{
"type": EntryType.MISC,
"type": "misc",
"fields": {
"author": "Newlines and spacing\neverywhere",
"title": "Still valid"
}
},
{
"type": EntryType.STANDARD,
"type": "standard",
"fields": {
"author": "Tests EntryType.STANDARD",
"title": "Formal standard ref"
}
},
{
"type": EntryType.IN_BOOK,
"type": "inbook",
"fields": {
"author": "Part of a book",
"title": "Chapter Title",
"booktitle": "Whole Book Title"
}
},
{
"type": EntryType.IN_COLLECTION,
"type": "incollection",
"fields": {
"author": "Self-contained part of a collection",
"title": "In Collection Title",
Expand Down