bnc-lookup 1.1.0__tar.gz → 1.2.0__tar.gz

{bnc_lookup-1.1.0 → bnc_lookup-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bnc-lookup
-Version: 1.1.0
+Version: 1.2.0
 Summary: Static Hash-Based Lookup for BNC Terms
 Home-page: https://github.com/craigtrim/bnc-lookup
 License: MIT
@@ -133,6 +133,16 @@ It's a **100-million-word corpus of real British English** collected from writte
 
 If a token passes the BNC test, you can be confident it's a word that real people actually use.
 
+## Real Words vs Dictionary Words
+
+How much of real-world English is in the dictionary? We compared BNC against WordNet:
+
+![BNC Vocabulary Zones by WordNet Coverage](https://raw.githubusercontent.com/craigtrim/bnc-lookup/master/docs/images/vocabulary_zones.png)
+
+**93%** of common words (bucket 1-10) are in WordNet. But dictionaries miss proper nouns, technical terms, compounds, and domain jargon that appear constantly in real text.
+
+That's the gap BNC fills. [Full analysis](https://github.com/craigtrim/bnc-lookup/issues/1)
+
 ## When to Use This
 
 - **Tokenization filtering**: Keep real words, discard garbage
@@ -186,6 +196,7 @@ This package contains data derived from the British National Corpus frequency li
 ## See Also
 
 - **[wordnet-lookup](https://github.com/craigtrim/wordnet-lookup)** - Similar O(1) lookup using the WordNet lexicon
+- **[BNC vs WordNet Analysis](https://github.com/craigtrim/bnc-lookup/issues/1)** - Deep dive on what each captures
 
 ## Links
 

{bnc_lookup-1.1.0 → bnc_lookup-1.2.0}/README.md

@@ -102,6 +102,16 @@ It's a **100-million-word corpus of real British English** collected from writte
 
 If a token passes the BNC test, you can be confident it's a word that real people actually use.
 
+## Real Words vs Dictionary Words
+
+How much of real-world English is in the dictionary? We compared BNC against WordNet:
+
+![BNC Vocabulary Zones by WordNet Coverage](https://raw.githubusercontent.com/craigtrim/bnc-lookup/master/docs/images/vocabulary_zones.png)
+
+**93%** of common words (bucket 1-10) are in WordNet. But dictionaries miss proper nouns, technical terms, compounds, and domain jargon that appear constantly in real text.
+
+That's the gap BNC fills. [Full analysis](https://github.com/craigtrim/bnc-lookup/issues/1)
+
 ## When to Use This
 
 - **Tokenization filtering**: Keep real words, discard garbage
@@ -155,6 +165,7 @@ This package contains data derived from the British National Corpus frequency li
 ## See Also
 
 - **[wordnet-lookup](https://github.com/craigtrim/wordnet-lookup)** - Similar O(1) lookup using the WordNet lexicon
+- **[BNC vs WordNet Analysis](https://github.com/craigtrim/bnc-lookup/issues/1)** - Deep dive on what each captures
 
 ## Links
 

bnc_lookup-1.2.0/bnc_lookup/__init__.py

@@ -0,0 +1,46 @@
+from bnc_lookup.find_bnc import FindBnc
+from bnc_lookup.find_freq import FindFreq
+from bnc_lookup.find_words import FindWords
+
+
+def exists(input_text: str) -> bool:
+    """Check if a word exists in the BNC corpus."""
+    return FindBnc().exists(input_text)
+
+
+def bucket(input_text: str) -> int | None:
+    """
+    Get frequency bucket for a word.
+
+    Returns:
+        1-100: Bucket number (1=most frequent, 100=least frequent)
+        None: Word not found in BNC
+    """
+    return FindFreq().bucket(input_text)
+
+
+def words(bucket: int) -> tuple:
+    """
+    Get all words in a frequency bucket.
+
+    Args:
+        bucket: Bucket number 1-100 (1=most frequent, 100=least frequent)
+
+    Returns:
+        Tuple of words in that bucket (alphabetically sorted)
+    """
+    return FindWords().by_bucket(bucket)
+
+
+def sample(bucket: int, n: int = 10) -> list:
+    """
+    Get random sample of words from a bucket.
+
+    Args:
+        bucket: Bucket number 1-100
+        n: Number of words to return (default 10)
+
+    Returns:
+        List of randomly sampled words
+    """
+    return FindWords().sample(bucket, n)

bnc_lookup-1.2.0/bnc_lookup/bw/__init__.py

@@ -0,0 +1,207 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+# AUTO-GENERATED - DO NOT MODIFY
+
+from .bw_01 import words_01
+from .bw_02 import words_02
+from .bw_03 import words_03
+from .bw_04 import words_04
+from .bw_05 import words_05
+from .bw_06 import words_06
+from .bw_07 import words_07
+from .bw_08 import words_08
+from .bw_09 import words_09
+from .bw_10 import words_10
+from .bw_11 import words_11
+from .bw_12 import words_12
+from .bw_13 import words_13
+from .bw_14 import words_14
+from .bw_15 import words_15
+from .bw_16 import words_16
+from .bw_17 import words_17
+from .bw_18 import words_18
+from .bw_19 import words_19
+from .bw_20 import words_20
+from .bw_21 import words_21
+from .bw_22 import words_22
+from .bw_23 import words_23
+from .bw_24 import words_24
+from .bw_25 import words_25
+from .bw_26 import words_26
+from .bw_27 import words_27
+from .bw_28 import words_28
+from .bw_29 import words_29
+from .bw_30 import words_30
+from .bw_31 import words_31
+from .bw_32 import words_32
+from .bw_33 import words_33
+from .bw_34 import words_34
+from .bw_35 import words_35
+from .bw_36 import words_36
+from .bw_37 import words_37
+from .bw_38 import words_38
+from .bw_39 import words_39
+from .bw_40 import words_40
+from .bw_41 import words_41
+from .bw_42 import words_42
+from .bw_43 import words_43
+from .bw_44 import words_44
+from .bw_45 import words_45
+from .bw_46 import words_46
+from .bw_47 import words_47
+from .bw_48 import words_48
+from .bw_49 import words_49
+from .bw_50 import words_50
+from .bw_51 import words_51
+from .bw_52 import words_52
+from .bw_53 import words_53
+from .bw_54 import words_54
+from .bw_55 import words_55
+from .bw_56 import words_56
+from .bw_57 import words_57
+from .bw_58 import words_58
+from .bw_59 import words_59
+from .bw_60 import words_60
+from .bw_61 import words_61
+from .bw_62 import words_62
+from .bw_63 import words_63
+from .bw_64 import words_64
+from .bw_65 import words_65
+from .bw_66 import words_66
+from .bw_67 import words_67
+from .bw_68 import words_68
+from .bw_69 import words_69
+from .bw_70 import words_70
+from .bw_71 import words_71
+from .bw_72 import words_72
+from .bw_73 import words_73
+from .bw_74 import words_74
+from .bw_75 import words_75
+from .bw_76 import words_76
+from .bw_77 import words_77
+from .bw_78 import words_78
+from .bw_79 import words_79
+from .bw_80 import words_80
+from .bw_81 import words_81
+from .bw_82 import words_82
+from .bw_83 import words_83
+from .bw_84 import words_84
+from .bw_85 import words_85
+from .bw_86 import words_86
+from .bw_87 import words_87
+from .bw_88 import words_88
+from .bw_89 import words_89
+from .bw_90 import words_90
+from .bw_91 import words_91
+from .bw_92 import words_92
+from .bw_93 import words_93
+from .bw_94 import words_94
+from .bw_95 import words_95
+from .bw_96 import words_96
+from .bw_97 import words_97
+from .bw_98 import words_98
+from .bw_99 import words_99
+from .bw_100 import words_100
+
+__all__ = [
+    'words_01',
+    'words_02',
+    'words_03',
+    'words_04',
+    'words_05',
+    'words_06',
+    'words_07',
+    'words_08',
+    'words_09',
+    'words_10',
+    'words_11',
+    'words_12',
+    'words_13',
+    'words_14',
+    'words_15',
+    'words_16',
+    'words_17',
+    'words_18',
+    'words_19',
+    'words_20',
+    'words_21',
+    'words_22',
+    'words_23',
+    'words_24',
+    'words_25',
+    'words_26',
+    'words_27',
+    'words_28',
+    'words_29',
+    'words_30',
+    'words_31',
+    'words_32',
+    'words_33',
+    'words_34',
+    'words_35',
+    'words_36',
+    'words_37',
+    'words_38',
+    'words_39',
+    'words_40',
+    'words_41',
+    'words_42',
+    'words_43',
+    'words_44',
+    'words_45',
+    'words_46',
+    'words_47',
+    'words_48',
+    'words_49',
+    'words_50',
+    'words_51',
+    'words_52',
+    'words_53',
+    'words_54',
+    'words_55',
+    'words_56',
+    'words_57',
+    'words_58',
+    'words_59',
+    'words_60',
+    'words_61',
+    'words_62',
+    'words_63',
+    'words_64',
+    'words_65',
+    'words_66',
+    'words_67',
+    'words_68',
+    'words_69',
+    'words_70',
+    'words_71',
+    'words_72',
+    'words_73',
+    'words_74',
+    'words_75',
+    'words_76',
+    'words_77',
+    'words_78',
+    'words_79',
+    'words_80',
+    'words_81',
+    'words_82',
+    'words_83',
+    'words_84',
+    'words_85',
+    'words_86',
+    'words_87',
+    'words_88',
+    'words_89',
+    'words_90',
+    'words_91',
+    'words_92',
+    'words_93',
+    'words_94',
+    'words_95',
+    'words_96',
+    'words_97',
+    'words_98',
+    'words_99',
+    'words_100',
+]