nepali_unicoder 0.1.1__tar.gz

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.
@@ -0,0 +1,21 @@
1
+ MIT License
2
+
3
+ Copyright (c) 2025 RealSanjeev
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in all
13
+ copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21
+ SOFTWARE.
@@ -0,0 +1 @@
1
+ include src/nepali_unicoder/*.json
@@ -0,0 +1,183 @@
1
+ Metadata-Version: 2.4
2
+ Name: nepali_unicoder
3
+ Version: 0.1.1
4
+ Summary: A Python package for Roman to Nepali (Devanagari) transliteration
5
+ Author-email: realsanjeev <075bei033.sanjeev@pcampus.edu.np>
6
+ License-Expression: MIT
7
+ Project-URL: Homepage, https://github.com/realsanjeev/nepali_unicoder
8
+ Keywords: nepali,unicoder,roman to devanagari,nepali transliteration,preeti to unicode
9
+ Classifier: Programming Language :: Python
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: Operating System :: OS Independent
12
+ Requires-Python: >=3.7
13
+ Description-Content-Type: text/markdown
14
+ License-File: LICENSE
15
+ Provides-Extra: dev
16
+ Requires-Dist: pre-commit; extra == "dev"
17
+ Dynamic: license-file
18
+
19
+ # Nepali Unicoder
20
+
21
+ A robust Python package for converting Romanized Nepali text and Preeti font text into Unicode Devanagari script. It uses a greedy matching algorithm for Roman transliteration and a two-phase conversion process for Preeti with contextual rules.
22
+
23
+ ## Features
24
+
25
+ - **Accurate Transliteration**: Uses a greedy matching algorithm to prioritize longer phonetic matches (e.g., 'kha' is matched before 'k' and 'h').
26
+ - **Preeti Font Support**: Full support for Preeti to Unicode conversion with 30+ contextual rules for accurate transformation.
27
+ - **Smart Vowel Handling**: Distinguishes between independent vowels (e.g., 'aa' -> 'आ') and vowel signs/matras (e.g., 'ka' -> 'क', 'kaa' -> 'का').
28
+ - **Contextual Rules**: Handles complex Devanagari rules like reph positioning, matra reordering, and special character combinations.
29
+ - **Mixed Content Support**: Allows keeping English words or specific text in Roman script using `{}` blocks.
30
+ - **Customizable**: Supports custom word-level overrides via `word_maps.json`.
31
+ - **CLI Support**: Can be used directly from the command line.
32
+
33
+ ## Installation
34
+
35
+ You can install the package locally:
36
+
37
+ ```bash
38
+ pip install nepali-unicoder
39
+ ```
40
+
41
+ ## Usage
42
+
43
+ ### Command Line Interface (CLI)
44
+
45
+ You can use the converter directly from the terminal:
46
+
47
+ ```bash
48
+ # Direct argument
49
+ python -m nepali_unicoder "namaste"
50
+ # Output: नमस्ते
51
+
52
+ # Pipe input
53
+ echo "mero naam sanjeev ho" | python -m nepali_unicoder
54
+ # Output: मेरो नाम सन्जीव् हो
55
+ ```
56
+
57
+ ### Python API
58
+
59
+ ```python
60
+ from nepali_unicoder.convert import Converter
61
+
62
+ converter = Converter()
63
+
64
+ # Basic conversion
65
+ text = "namaste nepal"
66
+ print(converter.convert(text))
67
+ # Output: नमस्ते नेपाल
68
+
69
+ # Using 'as-is' blocks for English text
70
+ mixed_text = "mero naam {Sanjeev} ho"
71
+ print(converter.convert(mixed_text))
72
+ # Output: मेरो नाम Sanjeev हो
73
+ ```
74
+
75
+ ### Preeti Mode
76
+
77
+ Convert Preeti font text to Unicode with full support for contextual rules:
78
+
79
+ ```python
80
+ from nepali_unicoder.convert import Converter
81
+
82
+ # Create converter in Preeti mode
83
+ preeti_converter = Converter(mode="preeti")
84
+
85
+ # Basic conversion
86
+ preeti_text = "s{sf" # Preeti characters
87
+ print(preeti_converter.convert(preeti_text))
88
+ # Output: र्कर्का
89
+
90
+ # The converter handles:
91
+ # - Reph positioning: { → र् (moves before consonant)
92
+ # - Matra reordering: l (ि) moves after consonant
93
+ # - Special m transformations
94
+ # - Vowel combinations
95
+ ```
96
+
97
+ #### Preeti Character Examples
98
+
99
+ | Preeti | Unicode | Description |
100
+ |--------|---------|-------------|
101
+ | `s` | `क` | Consonant ka |
102
+ | `s{` | `र्क` | Reph + ka (contextual) |
103
+ | `sl` | `कि` | ka + short i (reordered) |
104
+ | `qm` | `क्र` | Special m transformation |
105
+ | `!@#` | `१२३` | Nepali numbers |
106
+
107
+ #### CLI for Preeti
108
+
109
+ ```bash
110
+ python -m nepali_unicoder --preeti "s{sf"
111
+ # Output: र्कर्का
112
+ ```
113
+
114
+
115
+ ## Transliteration Rules
116
+
117
+ - **Consonants**: `k` -> `क्`, `ka` -> `क`, `kh` -> `ख्`, `kha` -> `ख`
118
+ - **Vowels**: `a` -> `अ`, `aa` -> `आ`, `i` -> `इ`, `u` -> `उ`
119
+ - **Matras**: `ki` -> `कि`, `ko` -> `को`
120
+ - **Special**: `.` -> `।`, `..` -> `॥`
121
+ - **Numbers**: `0-9` -> `०-९` (Decimal points are preserved: `1.5` -> `१.५`)
122
+
123
+ ## Advanced Usage
124
+
125
+ ### Handling Complex Text
126
+
127
+ The converter handles mixed content gracefully. You can use `{}` to keep text as-is (e.g., for English words or code snippets).
128
+
129
+ ```python
130
+ text = "mero naam {Sanjeev} ho ra ma 12.5 barsa ko bhaye."
131
+ print(converter.convert(text))
132
+ # Output: मेरो नाम Sanjeev हो र म १२.५ बर्स को भए।
133
+ ```
134
+
135
+ ### Configuration
136
+
137
+ The package uses `word_maps.json` for custom word-level overrides, located in the `src/nepali_unicoder` directory.
138
+
139
+ 1. **`word_maps.json`**: Defines custom word-level overrides. Use this for words that don't follow standard phonetic rules.
140
+
141
+ Example `word_maps.json`:
142
+ ```json
143
+ {
144
+ "nepal": "नेपाल",
145
+ "kathamandu": "काठमाडौँ"
146
+ }
147
+ ```
148
+
149
+ ## Contribution
150
+
151
+ We welcome contributions! Here's how you can help:
152
+
153
+ 1. **Clone the repository**:
154
+ ```bash
155
+ git clone https://github.com/realsanjeev/nepali_unicoder.git
156
+ cd nepali_unicoder
157
+ ```
158
+
159
+ 2. **Set up a virtual environment**:
160
+ ```bash
161
+ python3 -m venv .venv
162
+ source .venv/bin/activate
163
+ pip install -e .
164
+ ```
165
+
166
+ 3. **Run tests**:
167
+ ```bash
168
+ python -m unittest discover tests
169
+ ```
170
+
171
+ 4. **Submit a Pull Request**: Create a new branch, make your changes, and submit a PR.
172
+
173
+ ## Development
174
+
175
+ To run tests:
176
+
177
+ ```bash
178
+ python -m unittest discover tests
179
+ ```
180
+
181
+ ## License
182
+
183
+ [MIT](./LICENSE)
@@ -0,0 +1,165 @@
1
+ # Nepali Unicoder
2
+
3
+ A robust Python package for converting Romanized Nepali text and Preeti font text into Unicode Devanagari script. It uses a greedy matching algorithm for Roman transliteration and a two-phase conversion process for Preeti with contextual rules.
4
+
5
+ ## Features
6
+
7
+ - **Accurate Transliteration**: Uses a greedy matching algorithm to prioritize longer phonetic matches (e.g., 'kha' is matched before 'k' and 'h').
8
+ - **Preeti Font Support**: Full support for Preeti to Unicode conversion with 30+ contextual rules for accurate transformation.
9
+ - **Smart Vowel Handling**: Distinguishes between independent vowels (e.g., 'aa' -> 'आ') and vowel signs/matras (e.g., 'ka' -> 'क', 'kaa' -> 'का').
10
+ - **Contextual Rules**: Handles complex Devanagari rules like reph positioning, matra reordering, and special character combinations.
11
+ - **Mixed Content Support**: Allows keeping English words or specific text in Roman script using `{}` blocks.
12
+ - **Customizable**: Supports custom word-level overrides via `word_maps.json`.
13
+ - **CLI Support**: Can be used directly from the command line.
14
+
15
+ ## Installation
16
+
17
+ You can install the package locally:
18
+
19
+ ```bash
20
+ pip install nepali-unicoder
21
+ ```
22
+
23
+ ## Usage
24
+
25
+ ### Command Line Interface (CLI)
26
+
27
+ You can use the converter directly from the terminal:
28
+
29
+ ```bash
30
+ # Direct argument
31
+ python -m nepali_unicoder "namaste"
32
+ # Output: नमस्ते
33
+
34
+ # Pipe input
35
+ echo "mero naam sanjeev ho" | python -m nepali_unicoder
36
+ # Output: मेरो नाम सन्जीव् हो
37
+ ```
38
+
39
+ ### Python API
40
+
41
+ ```python
42
+ from nepali_unicoder.convert import Converter
43
+
44
+ converter = Converter()
45
+
46
+ # Basic conversion
47
+ text = "namaste nepal"
48
+ print(converter.convert(text))
49
+ # Output: नमस्ते नेपाल
50
+
51
+ # Using 'as-is' blocks for English text
52
+ mixed_text = "mero naam {Sanjeev} ho"
53
+ print(converter.convert(mixed_text))
54
+ # Output: मेरो नाम Sanjeev हो
55
+ ```
56
+
57
+ ### Preeti Mode
58
+
59
+ Convert Preeti font text to Unicode with full support for contextual rules:
60
+
61
+ ```python
62
+ from nepali_unicoder.convert import Converter
63
+
64
+ # Create converter in Preeti mode
65
+ preeti_converter = Converter(mode="preeti")
66
+
67
+ # Basic conversion
68
+ preeti_text = "s{sf" # Preeti characters
69
+ print(preeti_converter.convert(preeti_text))
70
+ # Output: र्कर्का
71
+
72
+ # The converter handles:
73
+ # - Reph positioning: { → र् (moves before consonant)
74
+ # - Matra reordering: l (ि) moves after consonant
75
+ # - Special m transformations
76
+ # - Vowel combinations
77
+ ```
78
+
79
+ #### Preeti Character Examples
80
+
81
+ | Preeti | Unicode | Description |
82
+ |--------|---------|-------------|
83
+ | `s` | `क` | Consonant ka |
84
+ | `s{` | `र्क` | Reph + ka (contextual) |
85
+ | `sl` | `कि` | ka + short i (reordered) |
86
+ | `qm` | `क्र` | Special m transformation |
87
+ | `!@#` | `१२३` | Nepali numbers |
88
+
89
+ #### CLI for Preeti
90
+
91
+ ```bash
92
+ python -m nepali_unicoder --preeti "s{sf"
93
+ # Output: र्कर्का
94
+ ```
95
+
96
+
97
+ ## Transliteration Rules
98
+
99
+ - **Consonants**: `k` -> `क्`, `ka` -> `क`, `kh` -> `ख्`, `kha` -> `ख`
100
+ - **Vowels**: `a` -> `अ`, `aa` -> `आ`, `i` -> `इ`, `u` -> `उ`
101
+ - **Matras**: `ki` -> `कि`, `ko` -> `को`
102
+ - **Special**: `.` -> `।`, `..` -> `॥`
103
+ - **Numbers**: `0-9` -> `०-९` (Decimal points are preserved: `1.5` -> `१.५`)
104
+
105
+ ## Advanced Usage
106
+
107
+ ### Handling Complex Text
108
+
109
+ The converter handles mixed content gracefully. You can use `{}` to keep text as-is (e.g., for English words or code snippets).
110
+
111
+ ```python
112
+ text = "mero naam {Sanjeev} ho ra ma 12.5 barsa ko bhaye."
113
+ print(converter.convert(text))
114
+ # Output: मेरो नाम Sanjeev हो र म १२.५ बर्स को भए।
115
+ ```
116
+
117
+ ### Configuration
118
+
119
+ The package uses `word_maps.json` for custom word-level overrides, located in the `src/nepali_unicoder` directory.
120
+
121
+ 1. **`word_maps.json`**: Defines custom word-level overrides. Use this for words that don't follow standard phonetic rules.
122
+
123
+ Example `word_maps.json`:
124
+ ```json
125
+ {
126
+ "nepal": "नेपाल",
127
+ "kathamandu": "काठमाडौँ"
128
+ }
129
+ ```
130
+
131
+ ## Contribution
132
+
133
+ We welcome contributions! Here's how you can help:
134
+
135
+ 1. **Clone the repository**:
136
+ ```bash
137
+ git clone https://github.com/realsanjeev/nepali_unicoder.git
138
+ cd nepali_unicoder
139
+ ```
140
+
141
+ 2. **Set up a virtual environment**:
142
+ ```bash
143
+ python3 -m venv .venv
144
+ source .venv/bin/activate
145
+ pip install -e .
146
+ ```
147
+
148
+ 3. **Run tests**:
149
+ ```bash
150
+ python -m unittest discover tests
151
+ ```
152
+
153
+ 4. **Submit a Pull Request**: Create a new branch, make your changes, and submit a PR.
154
+
155
+ ## Development
156
+
157
+ To run tests:
158
+
159
+ ```bash
160
+ python -m unittest discover tests
161
+ ```
162
+
163
+ ## License
164
+
165
+ [MIT](./LICENSE)
@@ -0,0 +1,36 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61.0"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "nepali_unicoder"
7
+ version = "0.1.1"
8
+ description = "A Python package for Roman to Nepali (Devanagari) transliteration"
9
+ authors = [
10
+ { name="realsanjeev", email="075bei033.sanjeev@pcampus.edu.np" },
11
+ ]
12
+ readme = "README.md"
13
+ license = "MIT"
14
+ requires-python = ">=3.7"
15
+ dependencies = []
16
+ classifiers = [
17
+ "Programming Language :: Python",
18
+ "Programming Language :: Python :: 3",
19
+ "Operating System :: OS Independent",
20
+ ]
21
+ keywords = ["nepali", "unicoder", "roman to devanagari", "nepali transliteration", "preeti to unicode"]
22
+
23
+
24
+ [project.urls]
25
+ "Homepage" = "https://github.com/realsanjeev/nepali_unicoder"
26
+
27
+ [project.optional-dependencies]
28
+ dev = ["pre-commit"]
29
+
30
+ [tool.pytest.ini_options]
31
+ pythonpath = [
32
+ "src"
33
+ ]
34
+ testpaths = [
35
+ "tests",
36
+ ]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
File without changes
@@ -0,0 +1,32 @@
1
+ import sys
2
+
3
+ from nepali_unicoder.convert import Converter
4
+
5
+
6
+ def main():
7
+ args = sys.argv[1:]
8
+ mode = "roman"
9
+
10
+ if "--preeti" in args:
11
+ mode = "preeti"
12
+ args.remove("--preeti")
13
+
14
+ if len(args) < 1:
15
+ # Check if there is stdin
16
+ if not sys.stdin.isatty():
17
+ input_text = sys.stdin.read()
18
+ else:
19
+ print('Usage: python -m nepali_unicoder "your roman text here"')
20
+ print(' python -m nepali_unicoder --preeti "your preeti text here"')
21
+ print(' or: echo "namaste" | python -m nepali_unicoder')
22
+ return
23
+ else:
24
+ input_text = " ".join(args)
25
+
26
+ converter = Converter(mode=mode)
27
+ result = converter.convert(input_text)
28
+ print(result)
29
+
30
+
31
+ if __name__ == "__main__":
32
+ main()
@@ -0,0 +1,13 @@
1
+ from nepali_unicoder.engine import Engine
2
+
3
+
4
+ class Converter:
5
+ """
6
+ Wrapper around Engine for backward compatibility.
7
+ """
8
+
9
+ def __init__(self, mode: str = "roman"):
10
+ self.engine = Engine(mode=mode)
11
+
12
+ def convert(self, text: str) -> str:
13
+ return self.engine.transliterate(text)
@@ -0,0 +1,97 @@
1
+ import re
2
+ from typing import Optional
3
+
4
+ from nepali_unicoder.loader import PreetiLoader, RuleLoader
5
+ from nepali_unicoder.rules import PREETI_TO_UNICODE_MAPPING
6
+ from nepali_unicoder.tokenizer import Tokenizer
7
+ from nepali_unicoder.trie import Trie
8
+
9
+
10
+ class Engine:
11
+ def __init__(
12
+ self,
13
+ trie: Optional[Trie] = None,
14
+ tokenizer: Optional[Tokenizer] = None,
15
+ mode: str = "roman",
16
+ ):
17
+ self.mode = mode
18
+ self.post_rules = []
19
+
20
+ if trie is None:
21
+ if mode == "preeti":
22
+ loader = PreetiLoader()
23
+ # Load post-processing rules for Preeti mode
24
+ self.post_rules = PREETI_TO_UNICODE_MAPPING.get("post_rules", [])
25
+ else:
26
+ loader = RuleLoader()
27
+ self.trie = loader.load()
28
+ else:
29
+ self.trie = trie
30
+
31
+ if tokenizer is None:
32
+ self.tokenizer = Tokenizer()
33
+ else:
34
+ self.tokenizer = tokenizer
35
+
36
+ def transliterate(self, text: str) -> str:
37
+ """
38
+ Convert Roman text to Devanagari using the Trie.
39
+ """
40
+ if not text:
41
+ return ""
42
+
43
+ tokens = self.tokenizer.tokenize(text)
44
+ result = []
45
+
46
+ for token in tokens:
47
+ if token.type == "BLOCK":
48
+ result.append(token.value)
49
+ elif token.type == "LITERAL":
50
+ result.append(token.value)
51
+ elif token.type == "NUMBER":
52
+ # Process Number chunk: transliterate digits, keep others (like .) as is
53
+ for char in token.value:
54
+ if char.isdigit():
55
+ # Use Trie to find digit mapping (digits are single chars in rules)
56
+ match_val, _ = self.trie.longest_match(char)
57
+ if match_val:
58
+ result.append(match_val)
59
+ else:
60
+ result.append(char)
61
+ else:
62
+ result.append(char)
63
+ elif token.type == "ROMAN":
64
+ # Process Roman chunk with Trie
65
+ chunk = token.value
66
+ idx = 0
67
+ chunk_len = len(chunk)
68
+
69
+ while idx < chunk_len:
70
+ # Try to find longest match starting at idx
71
+ sub = chunk[idx:]
72
+ match_val, match_len = self.trie.longest_match(sub)
73
+
74
+ if match_val:
75
+ result.append(match_val)
76
+ idx += match_len
77
+ else:
78
+ # No match, keep character as is
79
+ result.append(chunk[idx])
80
+ idx += 1
81
+
82
+ output = "".join(result)
83
+
84
+ # Apply post-processing rules for Preeti mode
85
+ if self.mode == "preeti" and self.post_rules:
86
+ output = self._apply_post_rules(output)
87
+
88
+ return output
89
+
90
+ def _apply_post_rules(self, text: str) -> str:
91
+ """
92
+ Apply post-processing rules (regex replacements) to the text.
93
+ Used for Preeti mode to handle contextual transformations.
94
+ """
95
+ for pattern, replacement in self.post_rules:
96
+ text = re.sub(pattern, replacement, text)
97
+ return text
@@ -0,0 +1,84 @@
1
+ import json
2
+ import os
3
+
4
+ from nepali_unicoder.rules import PREETI_TO_UNICODE_MAPPING, ROMAN_TO_UNICODE_RULES
5
+ from nepali_unicoder.trie import Trie
6
+
7
+
8
+ class RuleLoader:
9
+ def __init__(self):
10
+ self.word_maps_path = os.path.join(os.path.dirname(__file__), "word_maps.json")
11
+
12
+ def load(self) -> Trie:
13
+ """Load rules and custom mappings into a Trie."""
14
+ trie = Trie()
15
+ self._load_rules(trie)
16
+ self._load_custom_mappings(trie)
17
+ return trie
18
+
19
+ def _load_rules(self, trie: Trie):
20
+ data = ROMAN_TO_UNICODE_RULES
21
+
22
+ consonants = data.get("consonants", {})
23
+ vowels = data.get("vowels", {})
24
+ matras = data.get("matras", {})
25
+ special = data.get("special", {})
26
+ digits = data.get("digits", {})
27
+
28
+ # 1. Independent Vowels
29
+ for rom, dev in vowels.items():
30
+ trie.add(rom, dev)
31
+
32
+ # 2. Consonants and Combinations
33
+ halanta = "्"
34
+
35
+ for rom_cons, dev_cons in consonants.items():
36
+ # Case 1: Consonant alone (halanta form) -> 'k' -> 'क्'
37
+ trie.add(rom_cons, dev_cons + halanta)
38
+
39
+ # Case 2: Consonant + 'a' (Schwa form) -> 'ka' -> 'क'
40
+ trie.add(rom_cons + "a", dev_cons)
41
+
42
+ # Case 3: Consonant + other vowels -> 'ki' -> 'कि'
43
+ for rom_vowel, matra in matras.items():
44
+ if rom_vowel == "a":
45
+ continue # Handled above
46
+ trie.add(rom_cons + rom_vowel, dev_cons + matra)
47
+
48
+ # 3. Special, Digits, Punctuation
49
+ for rom, dev in special.items():
50
+ trie.add(rom, dev)
51
+
52
+ for rom, dev in digits.items():
53
+ trie.add(rom, dev)
54
+
55
+ # Ensure 'a' maps to 'अ' (already in vowels, but good to double check)
56
+ trie.add("a", vowels.get("a", "अ"))
57
+
58
+ def _load_custom_mappings(self, trie: Trie):
59
+ if not os.path.exists(self.word_maps_path):
60
+ return
61
+
62
+ try:
63
+ with open(self.word_maps_path, "r", encoding="utf-8") as f:
64
+ mappings = json.load(f)
65
+ for roman, devanagari in mappings.items():
66
+ trie.add(roman.lower(), devanagari)
67
+ except Exception as e:
68
+ print(f"Error reading word_maps.json: {e}")
69
+
70
+
71
+ class PreetiLoader:
72
+ def __init__(self):
73
+ pass
74
+
75
+ def load(self) -> Trie:
76
+ """Load Preeti rules into a Trie."""
77
+ trie = Trie()
78
+ data = PREETI_TO_UNICODE_MAPPING
79
+
80
+ mappings = data.get("mappings", {})
81
+ for key, value in mappings.items():
82
+ trie.add(key, value)
83
+
84
+ return trie