lexicora 0.1.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- lexicora/__init__.py +8 -0
- lexicora/cleaner.py +42 -0
- lexicora/correction.py +78 -0
- lexicora/models.py +24 -0
- lexicora/normalizer.py +56 -0
- lexicora/pipeline.py +27 -0
- lexicora-0.1.0.dist-info/METADATA +140 -0
- lexicora-0.1.0.dist-info/RECORD +10 -0
- lexicora-0.1.0.dist-info/WHEEL +4 -0
- lexicora-0.1.0.dist-info/licenses/LICENSE +201 -0
lexicora/__init__.py
ADDED
lexicora/cleaner.py
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
"""Whitespace, tab, and line-break cleaning for Lexicora."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
|
|
7
|
+
from .models import Change, OCRResult
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
def clean_whitespace(result: OCRResult) -> OCRResult:
|
|
11
|
+
"""Normalize tabs, line endings, repeated spaces, and repeated line breaks."""
|
|
12
|
+
original = result.text
|
|
13
|
+
|
|
14
|
+
# Normalize line endings: \r\n and \r → \n
|
|
15
|
+
text = result.text.replace("\r\n", "\n").replace("\r", "\n")
|
|
16
|
+
|
|
17
|
+
# Tabs → single space
|
|
18
|
+
text = text.replace("\t", " ")
|
|
19
|
+
|
|
20
|
+
# Collapse runs of spaces into one space
|
|
21
|
+
text = re.sub(r" +", " ", text)
|
|
22
|
+
|
|
23
|
+
# Collapse 2+ newlines into 1 (test expects Nama\n\nRifqi → Nama\nRifqi)
|
|
24
|
+
text = re.sub(r"\n{2,}", "\n", text)
|
|
25
|
+
|
|
26
|
+
# Strip leading/trailing whitespace per line
|
|
27
|
+
text = re.sub(r"^[ ]+|[ ]+$", "", text, flags=re.MULTILINE)
|
|
28
|
+
|
|
29
|
+
# Strip leading/trailing newlines
|
|
30
|
+
text = text.strip("\n")
|
|
31
|
+
|
|
32
|
+
if text != original:
|
|
33
|
+
result.changes.append(
|
|
34
|
+
Change(
|
|
35
|
+
original=original,
|
|
36
|
+
corrected=text,
|
|
37
|
+
reason="whitespace",
|
|
38
|
+
position=None,
|
|
39
|
+
)
|
|
40
|
+
)
|
|
41
|
+
result.text = text
|
|
42
|
+
return result
|
lexicora/correction.py
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
"""OCR artifact detection and correction for Lexicora."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
|
|
7
|
+
from .models import Change, OCRResult
|
|
8
|
+
|
|
9
|
+
# OCR confusion map: (wrong, right) pairs.
|
|
10
|
+
CONFUSION_RULES = [
|
|
11
|
+
("O", "0"),
|
|
12
|
+
("I", "1"),
|
|
13
|
+
("l", "1"),
|
|
14
|
+
("S", "5"),
|
|
15
|
+
("B", "8"),
|
|
16
|
+
]
|
|
17
|
+
|
|
18
|
+
# Tokenizer: split on word boundaries, treating -, _ as separators
|
|
19
|
+
# Matches: pure confusion-char sequences, alphanumeric words, or separators
|
|
20
|
+
_TOKEN_RE = re.compile(r"[0-9OIlSB]+|[A-Za-z]+|[^A-Za-z0-9]+")
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
def _is_numeric_candidate(token: str) -> bool:
|
|
24
|
+
"""Check if a token has a strong numeric profile for correction."""
|
|
25
|
+
if not token:
|
|
26
|
+
return False
|
|
27
|
+
digits = sum(1 for c in token if c.isdigit())
|
|
28
|
+
total = len(token)
|
|
29
|
+
return digits / total >= 0.5 and digits >= 1
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
def _correct_token(token: str) -> tuple[str, list[tuple[str, str, int]]]:
|
|
33
|
+
"""Apply confusion rules to a single token. Returns (corrected, [(old,new,pos)])."""
|
|
34
|
+
corrections: list[tuple[str, str, int]] = []
|
|
35
|
+
chars = list(token)
|
|
36
|
+
for wrong, right in CONFUSION_RULES:
|
|
37
|
+
for i, c in enumerate(chars):
|
|
38
|
+
if c == wrong:
|
|
39
|
+
chars[i] = right
|
|
40
|
+
corrections.append((wrong, right, i))
|
|
41
|
+
return "".join(chars), corrections
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
def correct_ocr_artifacts(result: OCRResult) -> OCRResult:
|
|
45
|
+
"""Detect and correct OCR character confusions in numeric-context tokens."""
|
|
46
|
+
text = result.text
|
|
47
|
+
changes: list[Change] = []
|
|
48
|
+
|
|
49
|
+
new_text = []
|
|
50
|
+
|
|
51
|
+
for match in _TOKEN_RE.finditer(text):
|
|
52
|
+
token = match.group(0)
|
|
53
|
+
start = match.start()
|
|
54
|
+
|
|
55
|
+
if _is_numeric_candidate(token):
|
|
56
|
+
corrected, char_corrections = _correct_token(token)
|
|
57
|
+
if corrected != token:
|
|
58
|
+
for old_char, new_char, char_pos in char_corrections:
|
|
59
|
+
changes.append(
|
|
60
|
+
Change(
|
|
61
|
+
original=old_char,
|
|
62
|
+
corrected=new_char,
|
|
63
|
+
reason="numeric_context",
|
|
64
|
+
position=start + char_pos,
|
|
65
|
+
)
|
|
66
|
+
)
|
|
67
|
+
new_text.append(corrected)
|
|
68
|
+
else:
|
|
69
|
+
new_text.append(token)
|
|
70
|
+
else:
|
|
71
|
+
new_text.append(token)
|
|
72
|
+
|
|
73
|
+
new_full = "".join(new_text)
|
|
74
|
+
if new_full != text:
|
|
75
|
+
result.text = new_full
|
|
76
|
+
result.changes.extend(changes)
|
|
77
|
+
|
|
78
|
+
return result
|
lexicora/models.py
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
"""Data models for Lexicora."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from dataclasses import dataclass, field
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
@dataclass
|
|
9
|
+
class Change:
|
|
10
|
+
"""A single correction made during processing."""
|
|
11
|
+
|
|
12
|
+
original: str
|
|
13
|
+
corrected: str
|
|
14
|
+
reason: str
|
|
15
|
+
position: int | None = None
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
@dataclass
|
|
19
|
+
class OCRResult:
|
|
20
|
+
"""Result of OCR post-processing."""
|
|
21
|
+
|
|
22
|
+
original: str
|
|
23
|
+
text: str
|
|
24
|
+
changes: list[Change] = field(default_factory=list)
|
lexicora/normalizer.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
"""Normalization for Lexicora: Unicode and punctuation."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
import unicodedata
|
|
7
|
+
|
|
8
|
+
from .models import Change, OCRResult
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def normalize_unicode(result: OCRResult) -> OCRResult:
|
|
12
|
+
"""Apply NFC Unicode normalization to the result text."""
|
|
13
|
+
normalized = unicodedata.normalize("NFC", result.text)
|
|
14
|
+
if normalized != result.text:
|
|
15
|
+
result.changes.append(
|
|
16
|
+
Change(
|
|
17
|
+
original=result.text,
|
|
18
|
+
corrected=normalized,
|
|
19
|
+
reason="unicode_nfc",
|
|
20
|
+
position=None,
|
|
21
|
+
)
|
|
22
|
+
)
|
|
23
|
+
result.text = normalized
|
|
24
|
+
return result
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
def normalize_punctuation(result: OCRResult) -> OCRResult:
|
|
28
|
+
"""Conservatively normalize common OCR punctuation spacing."""
|
|
29
|
+
original = result.text
|
|
30
|
+
text = result.text
|
|
31
|
+
|
|
32
|
+
# Remove space/tab before colon, comma, semicolon, period
|
|
33
|
+
text = re.sub(r"[ \t]+:([ ])", r":\1", text) # " : " → ": "
|
|
34
|
+
text = re.sub(r"[ \t]+:", ":", text) # " :" at end of line
|
|
35
|
+
text = re.sub(r"[ \t]+,", ",", text)
|
|
36
|
+
text = re.sub(r"[ \t]+;", ";", text)
|
|
37
|
+
text = re.sub(r"[ \t]+\.", ".", text)
|
|
38
|
+
|
|
39
|
+
# Collapse duplicated colons into one
|
|
40
|
+
text = re.sub(r":{2,}", ":", text)
|
|
41
|
+
|
|
42
|
+
# Ensure one space after colon when followed by a non-space char,
|
|
43
|
+
# but never split a time/ratio like "12:30" (digit on both sides).
|
|
44
|
+
text = re.sub(r"(?<!\d):(\S)", r": \1", text)
|
|
45
|
+
|
|
46
|
+
if text != original:
|
|
47
|
+
result.changes.append(
|
|
48
|
+
Change(
|
|
49
|
+
original=original,
|
|
50
|
+
corrected=text,
|
|
51
|
+
reason="punctuation",
|
|
52
|
+
position=None,
|
|
53
|
+
)
|
|
54
|
+
)
|
|
55
|
+
result.text = text
|
|
56
|
+
return result
|
lexicora/pipeline.py
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
"""Processing pipeline for Lexicora."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
from .cleaner import clean_whitespace
|
|
6
|
+
from .correction import correct_ocr_artifacts
|
|
7
|
+
from .models import OCRResult
|
|
8
|
+
from .normalizer import normalize_punctuation, normalize_unicode
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def clean_ocr(text: str) -> OCRResult:
|
|
12
|
+
"""Clean and normalize OCR output text.
|
|
13
|
+
|
|
14
|
+
Milestone 3 implements Unicode and whitespace normalization.
|
|
15
|
+
Milestone 4 adds context-aware OCR character correction.
|
|
16
|
+
"""
|
|
17
|
+
if not isinstance(text, str):
|
|
18
|
+
raise TypeError(f"expected str, got {type(text).__name__}")
|
|
19
|
+
|
|
20
|
+
result = OCRResult(original=text, text=text, changes=[])
|
|
21
|
+
|
|
22
|
+
result = normalize_unicode(result)
|
|
23
|
+
result = normalize_punctuation(result)
|
|
24
|
+
result = clean_whitespace(result)
|
|
25
|
+
result = correct_ocr_artifacts(result)
|
|
26
|
+
|
|
27
|
+
return result
|
|
@@ -0,0 +1,140 @@
|
|
|
1
|
+
Metadata-Version: 2.5
|
|
2
|
+
Name: lexicora
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Lightweight, deterministic OCR post-processing library for Python.
|
|
5
|
+
Author: Lexicora Contributors
|
|
6
|
+
License: Apache-2.0
|
|
7
|
+
License-File: LICENSE
|
|
8
|
+
Keywords: indonesian,ocr,post-processing,text-cleaning
|
|
9
|
+
Classifier: Development Status :: 3 - Alpha
|
|
10
|
+
Classifier: Intended Audience :: Developers
|
|
11
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
12
|
+
Classifier: Programming Language :: Python :: 3
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
17
|
+
Classifier: Topic :: Text Processing :: General
|
|
18
|
+
Requires-Python: >=3.10
|
|
19
|
+
Provides-Extra: dev
|
|
20
|
+
Requires-Dist: mypy>=1.13; extra == 'dev'
|
|
21
|
+
Requires-Dist: pytest>=8.0; extra == 'dev'
|
|
22
|
+
Requires-Dist: ruff>=0.8; extra == 'dev'
|
|
23
|
+
Description-Content-Type: text/markdown
|
|
24
|
+
|
|
25
|
+
# Lexicora
|
|
26
|
+
|
|
27
|
+
Lexicora is a lightweight, deterministic OCR post-processing library for Python.
|
|
28
|
+
It takes the raw text produced by an OCR engine (Tesseract, EasyOCR, PaddleOCR,
|
|
29
|
+
or any other) and turns it into cleaner, more usable text.
|
|
30
|
+
|
|
31
|
+
> **Lexicora is not an OCR engine.** It does not read images. It receives the
|
|
32
|
+
> text an OCR engine already produced and cleans it up.
|
|
33
|
+
|
|
34
|
+
**Status:** v0.1.0 — initial release
|
|
35
|
+
|
|
36
|
+
## Problem
|
|
37
|
+
|
|
38
|
+
OCR output is often noisy: duplicated spaces, inconsistent line breaks,
|
|
39
|
+
odd punctuation spacing, Unicode inconsistencies, and character confusions
|
|
40
|
+
such as `O` vs `0`, `I` vs `1`, or `l` vs `1`. Developers usually end up
|
|
41
|
+
writing custom post-processing code for every project. Lexicora aims to be a
|
|
42
|
+
reusable, lightweight layer that can be dropped after almost any OCR engine.
|
|
43
|
+
|
|
44
|
+
## Installation
|
|
45
|
+
|
|
46
|
+
```bash
|
|
47
|
+
pip install lexicora
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
Or, for local development:
|
|
51
|
+
|
|
52
|
+
```bash
|
|
53
|
+
pip install -e ".[dev]"
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
## Quick start
|
|
57
|
+
|
|
58
|
+
```python
|
|
59
|
+
from lexicora import clean_ocr
|
|
60
|
+
|
|
61
|
+
result = clean_ocr("Nama : RIFQI ALFINNUR")
|
|
62
|
+
print(result.text)
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
`clean_ocr()` returns an `OCRResult` with `.original`, `.text`, and `.changes`
|
|
66
|
+
(a list of `Change` records describing what was modified and why).
|
|
67
|
+
|
|
68
|
+
## Design principles
|
|
69
|
+
|
|
70
|
+
- **Lightweight** — no runtime dependencies, standard library only.
|
|
71
|
+
- **Deterministic** — same input + configuration produces the same output.
|
|
72
|
+
- **Explainable** — every modification is recorded with a reason.
|
|
73
|
+
- **Conservative** — when unsure, leave the text unchanged. A missed
|
|
74
|
+
correction is preferred over a false correction.
|
|
75
|
+
- **Extensible** — modular correction rules that future versions can extend
|
|
76
|
+
without redesigning the public API.
|
|
77
|
+
|
|
78
|
+
## Supported corrections
|
|
79
|
+
|
|
80
|
+
- whitespace cleanup;
|
|
81
|
+
- line-break normalization;
|
|
82
|
+
- Unicode (NFC) normalization;
|
|
83
|
+
- punctuation spacing;
|
|
84
|
+
- context-aware OCR character correction (`O↔0`, `I↔1`, `l↔1`, `S↔5`,
|
|
85
|
+
`B↔8`), applied per token, never by blind global replacement.
|
|
86
|
+
|
|
87
|
+
## Change tracking
|
|
88
|
+
|
|
89
|
+
Every change is recorded as a `Change(original, corrected, reason, position)`.
|
|
90
|
+
For example, the `reason` field takes values such as `numeric_context`,
|
|
91
|
+
`punctuation`, `whitespace`, and `unicode_nfc`:
|
|
92
|
+
|
|
93
|
+
```python
|
|
94
|
+
from lexicora import clean_ocr
|
|
95
|
+
|
|
96
|
+
for change in clean_ocr("NIK: 3273O12").changes:
|
|
97
|
+
print(change.reason, change.original, "->", change.corrected, change.position)
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
## Limitations
|
|
101
|
+
|
|
102
|
+
- Not an OCR engine; does not process images.
|
|
103
|
+
- No ML / LLM-based correction in v0.1.
|
|
104
|
+
- Correction is conservative: ambiguous text is left unchanged.
|
|
105
|
+
- No semantic or language-aware correction.
|
|
106
|
+
|
|
107
|
+
## Privacy
|
|
108
|
+
|
|
109
|
+
Lexicora processes text locally. It does not send your text to any external
|
|
110
|
+
API, does not persist your OCR content, and does not require network access
|
|
111
|
+
at runtime. There is no telemetry.
|
|
112
|
+
|
|
113
|
+
## Benchmark
|
|
114
|
+
|
|
115
|
+
Run the v0.1 benchmark with:
|
|
116
|
+
|
|
117
|
+
```bash
|
|
118
|
+
python -m benchmarks.lexicora_benchmark
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
## Development
|
|
122
|
+
|
|
123
|
+
```bash
|
|
124
|
+
pip install -e ".[dev]"
|
|
125
|
+
pytest
|
|
126
|
+
ruff check .
|
|
127
|
+
mypy src
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
## Roadmap
|
|
131
|
+
|
|
132
|
+
See `PRD_v01.md` for the v0.1 specification and the milestone plan.
|
|
133
|
+
|
|
134
|
+
## License
|
|
135
|
+
|
|
136
|
+
Apache License 2.0. See [LICENSE](LICENSE).
|
|
137
|
+
|
|
138
|
+
## Changelog
|
|
139
|
+
|
|
140
|
+
See [CHANGELOG.md](CHANGELOG.md) for release notes.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
lexicora/__init__.py,sha256=Jnuulv0-QVQ8v_Xr1AeCkIz7L8ozmNISxxRPAnKm6Bw,234
|
|
2
|
+
lexicora/cleaner.py,sha256=Xa9KbDJMwenQ_F6XxPMx24QZcq6n9U7R5Os9Fr0WkXc,1174
|
|
3
|
+
lexicora/correction.py,sha256=zwpS36m5RNQr4jt8Ez4vg6BWWn6bZVrrVMGWSHhv-_k,2399
|
|
4
|
+
lexicora/models.py,sha256=Urf1nL9pPsunb4aD0WCtkpWfLxC2mdQpzi-_JDjXV7M,439
|
|
5
|
+
lexicora/normalizer.py,sha256=QoBJgPKyw-Tj2PcS3Jrgd-LwaZQ8GoygkpmG5E5bCok,1716
|
|
6
|
+
lexicora/pipeline.py,sha256=dXk1qISrl2EIUTgP1P6CjQHJis_SwYJYqEZ9Mg1BpQQ,825
|
|
7
|
+
lexicora-0.1.0.dist-info/METADATA,sha256=Yz-k1URy4a50RFF9hXMNpheM3Pl4PDKE1bj-IwgfweY,4048
|
|
8
|
+
lexicora-0.1.0.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
|
|
9
|
+
lexicora-0.1.0.dist-info/licenses/LICENSE,sha256=oN9L-UwSLZZoJG2pDhycJuOVSjIYQxoJX5rzCfEfDKo,11353
|
|
10
|
+
lexicora-0.1.0.dist-info/RECORD,,
|
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but not
|
|
32
|
+
limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2026 Lexicora Contributors
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|