py-text-toolkit 0.1.0__tar.gz

py_text_toolkit-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Dawood Afzal
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

py_text_toolkit-0.1.0/PKG-INFO

@@ -0,0 +1,262 @@
+Metadata-Version: 2.4
+Name: py-text-toolkit
+Version: 0.1.0
+Summary: A comprehensive string utility library for Python.
+Author-email: Dawood Afzal <dawoodafzal.62138@gmail.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: emoji>=2.0.0
+Dynamic: license-file
+
+# py-text-toolkit
+
+A lightweight, dependency-minimal Python library for everyday string operations — cleaning, validation, analysis, case conversion, and generation.
+
+---
+
+## Installation
+
+```bash
+pip install py-text-toolkit
+```
+
+> **Requires:** Python 3.8+  
+> **Optional dependency:** `emoji` (required only for `cleaning.remove_emojis`)
+
+---
+
+## Modules at a Glance
+
+| Module | What it does |
+|---|---|
+| `py-text-toolkit.cleaning` | Strip, replace, and normalize raw text |
+| `py-text-toolkit.validation` | Validate emails, URLs, passwords, and character sets |
+| `py-text-toolkit.analysis` | Count, compare, and measure strings |
+| `py-text-toolkit.format_cases` | Convert between naming conventions and formatting styles |
+| `py-text-toolkit.generation` | Generate slugs, masks, ciphers, and reversed strings |
+
+---
+
+## Quick Start
+
+```python
+from py-text-toolkit.cleaning import remove_html_tags, remove_urls
+from py-text-toolkit.validation import is_email, is_strong_password
+from py-text-toolkit.analysis import word_count, is_palindrome
+from py-text-toolkit.format_cases import to_snake_case, to_camel_case
+from py-text-toolkit.generation import generate_slug, mask_range
+
+# Clean
+remove_html_tags("<p>Hello <b>world</b></p>")   # "Hello world"
+remove_urls("Visit https://example.com today")  # "Visit today"
+
+# Validate
+is_email("user@example.com")        # True
+is_strong_password("Passw0rd!")     # True
+
+# Analyse
+word_count("Hello, world!")         # 2
+is_palindrome("A man a plan a canal Panama")  # True
+
+# Convert case
+to_snake_case("camelCaseText")      # "camel_case_text"
+to_camel_case("hello_world")        # "helloWorld"
+
+# Generate
+generate_slug("Hello World!")       # "hello-world"
+mask_range("1234-5678-9012", 5, 9, "*")  # "1234-****-9012"
+```
+
+---
+
+## Module Reference
+
+### `py-text-toolkit.cleaning`
+
+Functions for sanitising and normalising raw text.
+
+| Function | Signature | Description |
+|---|---|---|
+| `normalize_whitespace` | `(text) → str` | Collapse all whitespace runs to a single space and strip ends |
+| `remove_punctuation` | `(text, replace="") → str` | Remove or replace all punctuation characters |
+| `remove_digits` | `(text, replace="") → str` | Remove or replace all digit characters |
+| `remove_html_tags` | `(text, replace="") → str` | Strip or replace HTML tags |
+| `remove_urls` | `(text, replace="") → str` | Remove or replace HTTP/HTTPS and `www.` URLs |
+| `remove_emojis` | `(text, replace="") → str` | Remove or replace emoji characters (requires `emoji`) |
+| `collapse_spaces` | `(text) → str` | Remove **all** whitespace (not just collapse) |
+
+All cleaning functions accept an optional `replace` argument — the string substituted in place of each removed element (defaults to `""`). After replacement, whitespace is always normalized.
+
+```python
+from py-text-toolkit.cleaning import remove_punctuation, remove_html_tags, remove_emojis
+
+remove_punctuation("Hello, world!")              # "Hello world"
+remove_punctuation("Hello, world!", replace=" ") # "Hello world"
+
+remove_html_tags("<p>Hello <b>world</b></p>")    # "Hello world"
+remove_html_tags("<br/>line1<br/>line2", replace=" ")  # "line1 line2"
+
+remove_emojis("Great job! 🎉")                   # "Great job!"
+remove_emojis("Hello 😊", replace="[emoji]")     # "Hello [emoji]"
+```
+
+---
+
+### `py-text-toolkit.validation`
+
+Boolean predicates for common string formats.
+
+| Function | Signature | Description |
+|---|---|---|
+| `is_email` | `(text) → bool` | Check for a valid email address |
+| `is_url` | `(text) → bool` | Check for a valid HTTP or HTTPS URL |
+| `contains_only` | `(text, allowed_chars) → bool` | Check that every character is in the allowed set |
+| `is_strong_password` | `(text) → bool` | Check that a password meets strength requirements |
+
+**Password requirements** (`is_strong_password`):
+- Minimum 8 characters
+- At least one lowercase letter
+- At least one uppercase letter
+- At least one digit
+- At least one special character from `@$!%*?&`
+
+```python
+from py-text-toolkit.validation import is_email, is_url, contains_only, is_strong_password
+
+is_email("user@example.com")          # True
+is_email("not-an-email")              # False
+
+is_url("https://api.service.io/v1")   # True
+is_url("ftp://files.example.com")     # False
+
+contains_only("12345", "0123456789")  # True
+contains_only("hello!", "a-z")        # False  (literal chars only, not a range)
+
+is_strong_password("Passw0rd!")       # True
+is_strong_password("weakpass")        # False
+```
+
+> **Note on `contains_only`:** `allowed_chars` is treated as a set of literal characters. Special regex characters are escaped automatically, so `"a-z"` matches only the three characters `a`, `-`, and `z`, **not** a range.
+
+---
+
+### `py-text-toolkit.analysis`
+
+Functions that measure and compare strings.
+
+| Function | Signature | Description |
+|---|---|---|
+| `word_count` | `(text) → int` | Count words using regex word-boundary matching |
+| `char_frequency` | `(text, char) → int` | Count non-overlapping occurrences of a character or substring |
+| `count_vowels` | `(text) → int` | Count English vowels (a e i o u), case-insensitive |
+| `longest_word` | `(text) → int` | Return the length of the longest whitespace-delimited word |
+| `is_palindrome` | `(text, case_sensitive=False, ignore_formatting=True) → bool` | Check if a string is a palindrome |
+| `is_anagram` | `(word1, word2) → bool` | Check if two strings are anagrams (case-insensitive, ignores spaces) |
+
+```python
+from py-text-toolkit.analysis import word_count, is_palindrome, is_anagram, char_frequency
+
+word_count("Hello, world!")                   # 2
+word_count("  spaces   everywhere  ")         # 2
+
+char_frequency("banana", "an")                # 2
+
+is_palindrome("racecar")                      # True
+is_palindrome("A man a plan a canal Panama")  # True
+is_palindrome("Racecar", case_sensitive=True) # False
+
+is_anagram("listen", "silent")                # True
+is_anagram("Astronomer", "Moon starer")       # True
+```
+
+---
+
+### `py-text-toolkit.format_cases`
+
+Convert strings between naming conventions and apply text formatting.
+
+| Function | Signature | Description |
+|---|---|---|
+| `to_snake_case` | `(text) → str` | Convert to `snake_case` |
+| `to_camel_case` | `(text) → str` | Convert to `camelCase` |
+| `to_pascal_case` | `(text) → str` | Convert to `PascalCase` |
+| `to_kebab_case` | `(text) → str` | Convert to `kebab-case` |
+| `to_title_case` | `(text) → str` | Convert to `Title Case` |
+| `truncate` | `(text, max_length, suffix="...") → str` | Truncate to a maximum length with a suffix |
+| `pad_center` | `(text, width, fillchar=" ") → str` | Center-pad to a given width |
+
+All case converters handle mixed input (camelCase, PascalCase, snake_case, kebab-case, spaces).
+
+```python
+from py-text-toolkit.format_cases import to_snake_case, to_camel_case, truncate, pad_center
+
+to_snake_case("camelCaseText")    # "camel_case_text"
+to_snake_case("Hello World!")     # "hello_world"
+
+to_camel_case("hello_world")      # "helloWorld"
+to_camel_case("PascalCaseText")   # "pascalCaseText"
+
+to_pascal_case("kebab-case-text") # "KebabCaseText"
+to_kebab_case("camelCaseText")    # "camel-case-text"
+to_title_case("hello_world")      # "Hello World"
+
+truncate("Hello, World!", 8)      # "Hello..."
+truncate("Hi", 10)                # "Hi"
+
+pad_center("hello", 11)           # "   hello   "
+pad_center("hi", 10, "-")         # "----hi----"
+```
+
+---
+
+### `py-text-toolkit.generation`
+
+Functions that produce new strings from existing ones.
+
+| Function | Signature | Description |
+|---|---|---|
+| `generate_slug` | `(text) → str` | Convert to a URL-friendly slug |
+| `reverse_word` | `(text) → str` | Reverse all characters |
+| `mask_range` | `(text, start_index, end_index, placeholder="X") → str` | Mask a character range with a placeholder |
+| `ceasar_cipher` | `(text, shift) → str` | Encrypt/decrypt with the Caesar cipher |
+
+```python
+from py-text-toolkit.generation import generate_slug, mask_range, ceasar_cipher, reverse_word
+
+generate_slug("Hello World!")               # "hello-world"
+generate_slug("Python 3.11 -- Release Notes")  # "python-3-11-release-notes"
+
+reverse_word("hello")                       # "olleh"
+
+mask_range("1234-5678-9012", 5, 9, "*")     # "1234-****-9012"
+mask_range("secret", -3, -1)               # "secXXt"
+
+ceasar_cipher("Hello, World!", 3)           # "Khoor, Zruog!"
+ceasar_cipher("Khoor, Zruog!", -3)          # "Hello, World!"  (decrypt)
+```
+
+---
+
+## Dependencies
+
+| Package | Required | Used by |
+|---|---|---|
+| `re` (stdlib) | Always | All modules |
+| `string` (stdlib) | Always | `cleaning` |
+| `emoji` | Optional | `cleaning.remove_emojis` only |
+
+Install with the optional dependency:
+
+```bash
+pip install py-text-toolkit[emoji]
+```
+
+---
+
+## License
+
+MIT License — see [LICENSE](LICENSE) for details.

py_text_toolkit-0.1.0/README.md

@@ -0,0 +1,248 @@
+# py-text-toolkit
+
+A lightweight, dependency-minimal Python library for everyday string operations — cleaning, validation, analysis, case conversion, and generation.
+
+---
+
+## Installation
+
+```bash
+pip install py-text-toolkit
+```
+
+> **Requires:** Python 3.8+  
+> **Optional dependency:** `emoji` (required only for `cleaning.remove_emojis`)
+
+---
+
+## Modules at a Glance
+
+| Module | What it does |
+|---|---|
+| `py-text-toolkit.cleaning` | Strip, replace, and normalize raw text |
+| `py-text-toolkit.validation` | Validate emails, URLs, passwords, and character sets |
+| `py-text-toolkit.analysis` | Count, compare, and measure strings |
+| `py-text-toolkit.format_cases` | Convert between naming conventions and formatting styles |
+| `py-text-toolkit.generation` | Generate slugs, masks, ciphers, and reversed strings |
+
+---
+
+## Quick Start
+
+```python
+from py-text-toolkit.cleaning import remove_html_tags, remove_urls
+from py-text-toolkit.validation import is_email, is_strong_password
+from py-text-toolkit.analysis import word_count, is_palindrome
+from py-text-toolkit.format_cases import to_snake_case, to_camel_case
+from py-text-toolkit.generation import generate_slug, mask_range
+
+# Clean
+remove_html_tags("<p>Hello <b>world</b></p>")   # "Hello world"
+remove_urls("Visit https://example.com today")  # "Visit today"
+
+# Validate
+is_email("user@example.com")        # True
+is_strong_password("Passw0rd!")     # True
+
+# Analyse
+word_count("Hello, world!")         # 2
+is_palindrome("A man a plan a canal Panama")  # True
+
+# Convert case
+to_snake_case("camelCaseText")      # "camel_case_text"
+to_camel_case("hello_world")        # "helloWorld"
+
+# Generate
+generate_slug("Hello World!")       # "hello-world"
+mask_range("1234-5678-9012", 5, 9, "*")  # "1234-****-9012"
+```
+
+---
+
+## Module Reference
+
+### `py-text-toolkit.cleaning`
+
+Functions for sanitising and normalising raw text.
+
+| Function | Signature | Description |
+|---|---|---|
+| `normalize_whitespace` | `(text) → str` | Collapse all whitespace runs to a single space and strip ends |
+| `remove_punctuation` | `(text, replace="") → str` | Remove or replace all punctuation characters |
+| `remove_digits` | `(text, replace="") → str` | Remove or replace all digit characters |
+| `remove_html_tags` | `(text, replace="") → str` | Strip or replace HTML tags |
+| `remove_urls` | `(text, replace="") → str` | Remove or replace HTTP/HTTPS and `www.` URLs |
+| `remove_emojis` | `(text, replace="") → str` | Remove or replace emoji characters (requires `emoji`) |
+| `collapse_spaces` | `(text) → str` | Remove **all** whitespace (not just collapse) |
+
+All cleaning functions accept an optional `replace` argument — the string substituted in place of each removed element (defaults to `""`). After replacement, whitespace is always normalized.
+
+```python
+from py-text-toolkit.cleaning import remove_punctuation, remove_html_tags, remove_emojis
+
+remove_punctuation("Hello, world!")              # "Hello world"
+remove_punctuation("Hello, world!", replace=" ") # "Hello world"
+
+remove_html_tags("<p>Hello <b>world</b></p>")    # "Hello world"
+remove_html_tags("<br/>line1<br/>line2", replace=" ")  # "line1 line2"
+
+remove_emojis("Great job! 🎉")                   # "Great job!"
+remove_emojis("Hello 😊", replace="[emoji]")     # "Hello [emoji]"
+```
+
+---
+
+### `py-text-toolkit.validation`
+
+Boolean predicates for common string formats.
+
+| Function | Signature | Description |
+|---|---|---|
+| `is_email` | `(text) → bool` | Check for a valid email address |
+| `is_url` | `(text) → bool` | Check for a valid HTTP or HTTPS URL |
+| `contains_only` | `(text, allowed_chars) → bool` | Check that every character is in the allowed set |
+| `is_strong_password` | `(text) → bool` | Check that a password meets strength requirements |
+
+**Password requirements** (`is_strong_password`):
+- Minimum 8 characters
+- At least one lowercase letter
+- At least one uppercase letter
+- At least one digit
+- At least one special character from `@$!%*?&`
+
+```python
+from py-text-toolkit.validation import is_email, is_url, contains_only, is_strong_password
+
+is_email("user@example.com")          # True
+is_email("not-an-email")              # False
+
+is_url("https://api.service.io/v1")   # True
+is_url("ftp://files.example.com")     # False
+
+contains_only("12345", "0123456789")  # True
+contains_only("hello!", "a-z")        # False  (literal chars only, not a range)
+
+is_strong_password("Passw0rd!")       # True
+is_strong_password("weakpass")        # False
+```
+
+> **Note on `contains_only`:** `allowed_chars` is treated as a set of literal characters. Special regex characters are escaped automatically, so `"a-z"` matches only the three characters `a`, `-`, and `z`, **not** a range.
+
+---
+
+### `py-text-toolkit.analysis`
+
+Functions that measure and compare strings.
+
+| Function | Signature | Description |
+|---|---|---|
+| `word_count` | `(text) → int` | Count words using regex word-boundary matching |
+| `char_frequency` | `(text, char) → int` | Count non-overlapping occurrences of a character or substring |
+| `count_vowels` | `(text) → int` | Count English vowels (a e i o u), case-insensitive |
+| `longest_word` | `(text) → int` | Return the length of the longest whitespace-delimited word |
+| `is_palindrome` | `(text, case_sensitive=False, ignore_formatting=True) → bool` | Check if a string is a palindrome |
+| `is_anagram` | `(word1, word2) → bool` | Check if two strings are anagrams (case-insensitive, ignores spaces) |
+
+```python
+from py-text-toolkit.analysis import word_count, is_palindrome, is_anagram, char_frequency
+
+word_count("Hello, world!")                   # 2
+word_count("  spaces   everywhere  ")         # 2
+
+char_frequency("banana", "an")                # 2
+
+is_palindrome("racecar")                      # True
+is_palindrome("A man a plan a canal Panama")  # True
+is_palindrome("Racecar", case_sensitive=True) # False
+
+is_anagram("listen", "silent")                # True
+is_anagram("Astronomer", "Moon starer")       # True
+```
+
+---
+
+### `py-text-toolkit.format_cases`
+
+Convert strings between naming conventions and apply text formatting.
+
+| Function | Signature | Description |
+|---|---|---|
+| `to_snake_case` | `(text) → str` | Convert to `snake_case` |
+| `to_camel_case` | `(text) → str` | Convert to `camelCase` |
+| `to_pascal_case` | `(text) → str` | Convert to `PascalCase` |
+| `to_kebab_case` | `(text) → str` | Convert to `kebab-case` |
+| `to_title_case` | `(text) → str` | Convert to `Title Case` |
+| `truncate` | `(text, max_length, suffix="...") → str` | Truncate to a maximum length with a suffix |
+| `pad_center` | `(text, width, fillchar=" ") → str` | Center-pad to a given width |
+
+All case converters handle mixed input (camelCase, PascalCase, snake_case, kebab-case, spaces).
+
+```python
+from py-text-toolkit.format_cases import to_snake_case, to_camel_case, truncate, pad_center
+
+to_snake_case("camelCaseText")    # "camel_case_text"
+to_snake_case("Hello World!")     # "hello_world"
+
+to_camel_case("hello_world")      # "helloWorld"
+to_camel_case("PascalCaseText")   # "pascalCaseText"
+
+to_pascal_case("kebab-case-text") # "KebabCaseText"
+to_kebab_case("camelCaseText")    # "camel-case-text"
+to_title_case("hello_world")      # "Hello World"
+
+truncate("Hello, World!", 8)      # "Hello..."
+truncate("Hi", 10)                # "Hi"
+
+pad_center("hello", 11)           # "   hello   "
+pad_center("hi", 10, "-")         # "----hi----"
+```
+
+---
+
+### `py-text-toolkit.generation`
+
+Functions that produce new strings from existing ones.
+
+| Function | Signature | Description |
+|---|---|---|
+| `generate_slug` | `(text) → str` | Convert to a URL-friendly slug |
+| `reverse_word` | `(text) → str` | Reverse all characters |
+| `mask_range` | `(text, start_index, end_index, placeholder="X") → str` | Mask a character range with a placeholder |
+| `ceasar_cipher` | `(text, shift) → str` | Encrypt/decrypt with the Caesar cipher |
+
+```python
+from py-text-toolkit.generation import generate_slug, mask_range, ceasar_cipher, reverse_word
+
+generate_slug("Hello World!")               # "hello-world"
+generate_slug("Python 3.11 -- Release Notes")  # "python-3-11-release-notes"
+
+reverse_word("hello")                       # "olleh"
+
+mask_range("1234-5678-9012", 5, 9, "*")     # "1234-****-9012"
+mask_range("secret", -3, -1)               # "secXXt"
+
+ceasar_cipher("Hello, World!", 3)           # "Khoor, Zruog!"
+ceasar_cipher("Khoor, Zruog!", -3)          # "Hello, World!"  (decrypt)
+```
+
+---
+
+## Dependencies
+
+| Package | Required | Used by |
+|---|---|---|
+| `re` (stdlib) | Always | All modules |
+| `string` (stdlib) | Always | `cleaning` |
+| `emoji` | Optional | `cleaning.remove_emojis` only |
+
+Install with the optional dependency:
+
+```bash
+pip install py-text-toolkit[emoji]
+```
+
+---
+
+## License
+
+MIT License — see [LICENSE](LICENSE) for details.