input-cleaner 0.1.0__tar.gz

input_cleaner-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

input_cleaner-0.1.0/PKG-INFO

@@ -0,0 +1,177 @@
+Metadata-Version: 2.4
+Name: input_cleaner
+Version: 0.1.0
+Summary: Text cleaning, scoring and compression pipeline
+Author: marlon(MARLM8)
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tiktoken
+Dynamic: license-file
+
+# Input Cleaner
+
+Lightweight text preprocessing pipeline for cleaning, scoring and compressing user input.
+
+Designed for LLM optimization, noise reduction and token efficiency.
+
+---
+
+## Features
+
+* Text normalization and cleanup
+* Noise detection using heuristic scoring
+* Input compression (removes low-value words)
+* Quality scoring system (0–100)
+* Smart truncation for long inputs
+* Token reduction tracking using `tiktoken`
+
+---
+
+## Installation
+
+```bash
+pip install input_cleaner
+```
+
+Or local development:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick Start
+
+```python
+from input_cleaner import process
+
+result = process("hello hello I really really need help with this")
+
+print(result)
+```
+
+---
+
+## Example Output
+
+```json
+{
+  "original": "hello hello I really really need help with this",
+  "cleaned": "hello i really need help with this",
+  "compressed": "need help this",
+  "score": 78,
+  "status": "compress",
+  "output": "need help this",
+  "token_reduction": 0.32
+}
+```
+
+---
+
+## Pipeline Overview
+
+The system processes text in 4 stages:
+
+1. **Cleaning**
+
+   * Normalize text (lowercase, symbols)
+   * Remove duplicates and noise patterns
+
+2. **Compression**
+
+   * Remove weak or redundant words
+   * Preserve important tokens
+
+3. **Scoring**
+
+   * Evaluate text quality using:
+
+     * entropy
+     * character diversity
+     * vowel ratio
+     * pattern detection
+
+4. **Decision**
+
+   * Block low-quality input
+   * Compress medium-quality input
+   * Accept high-quality input
+   * Truncate long input if needed
+
+---
+
+## Status Values
+
+| Status              | Meaning               |
+| ------------------- | --------------------- |
+| `blocked_empty`     | Empty input           |
+| `blocked_low_score` | Low quality score     |
+| `blocked_noise`     | Likely random string  |
+| `blocked_low_info`  | Too short / low value |
+| `accepted_short`    | Short but valid       |
+| `compress`          | Needs compression     |
+| `truncated_smart`   | Long input trimmed    |
+| `accepted`          | Fully valid           |
+
+---
+
+## Use Cases
+
+* Preprocessing user input for LLMs
+* Reducing token costs
+* Filtering spam or noisy text
+* Improving prompt quality
+* Input validation layer for APIs
+
+---
+
+## Requirements
+
+* Python 3.8+
+* `tiktoken`
+
+---
+
+## Project Structure
+
+```bash
+text_pipeline/
+├── cleaner.py
+├── compressor.py
+├── scorer.py
+├── decision.py
+└── pipeline.py
+```
+
+---
+
+## Design Goals
+
+* Fast (pure Python, no heavy dependencies)
+* Deterministic (no randomness)
+* Modular (each step isolated)
+* Easy to extend
+
+---
+
+## Roadmap 
+
+* Add trigram scoring
+* Language detection
+* Configurable thresholds
+* FastAPI wrapper
+* Streaming support
+
+---
+
+## License
+
+Apache-2.0
+
+---
+
+## Author
+
+marlon (MARLM8)

input_cleaner-0.1.0/README.md

@@ -0,0 +1,166 @@
+# Input Cleaner
+
+Lightweight text preprocessing pipeline for cleaning, scoring and compressing user input.
+
+Designed for LLM optimization, noise reduction and token efficiency.
+
+---
+
+## Features
+
+* Text normalization and cleanup
+* Noise detection using heuristic scoring
+* Input compression (removes low-value words)
+* Quality scoring system (0–100)
+* Smart truncation for long inputs
+* Token reduction tracking using `tiktoken`
+
+---
+
+## Installation
+
+```bash
+pip install input_cleaner
+```
+
+Or local development:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick Start
+
+```python
+from input_cleaner import process
+
+result = process("hello hello I really really need help with this")
+
+print(result)
+```
+
+---
+
+## Example Output
+
+```json
+{
+  "original": "hello hello I really really need help with this",
+  "cleaned": "hello i really need help with this",
+  "compressed": "need help this",
+  "score": 78,
+  "status": "compress",
+  "output": "need help this",
+  "token_reduction": 0.32
+}
+```
+
+---
+
+## Pipeline Overview
+
+The system processes text in 4 stages:
+
+1. **Cleaning**
+
+   * Normalize text (lowercase, symbols)
+   * Remove duplicates and noise patterns
+
+2. **Compression**
+
+   * Remove weak or redundant words
+   * Preserve important tokens
+
+3. **Scoring**
+
+   * Evaluate text quality using:
+
+     * entropy
+     * character diversity
+     * vowel ratio
+     * pattern detection
+
+4. **Decision**
+
+   * Block low-quality input
+   * Compress medium-quality input
+   * Accept high-quality input
+   * Truncate long input if needed
+
+---
+
+## Status Values
+
+| Status              | Meaning               |
+| ------------------- | --------------------- |
+| `blocked_empty`     | Empty input           |
+| `blocked_low_score` | Low quality score     |
+| `blocked_noise`     | Likely random string  |
+| `blocked_low_info`  | Too short / low value |
+| `accepted_short`    | Short but valid       |
+| `compress`          | Needs compression     |
+| `truncated_smart`   | Long input trimmed    |
+| `accepted`          | Fully valid           |
+
+---
+
+## Use Cases
+
+* Preprocessing user input for LLMs
+* Reducing token costs
+* Filtering spam or noisy text
+* Improving prompt quality
+* Input validation layer for APIs
+
+---
+
+## Requirements
+
+* Python 3.8+
+* `tiktoken`
+
+---
+
+## Project Structure
+
+```bash
+text_pipeline/
+├── cleaner.py
+├── compressor.py
+├── scorer.py
+├── decision.py
+└── pipeline.py
+```
+
+---
+
+## Design Goals
+
+* Fast (pure Python, no heavy dependencies)
+* Deterministic (no randomness)
+* Modular (each step isolated)
+* Easy to extend
+
+---
+
+## Roadmap 
+
+* Add trigram scoring
+* Language detection
+* Configurable thresholds
+* FastAPI wrapper
+* Streaming support
+
+---
+
+## License
+
+Apache-2.0
+
+---
+
+## Author
+
+marlon (MARLM8)

input_cleaner-0.1.0/input_cleaner/__init__.py

@@ -0,0 +1,5 @@
+# __init__.py
+
+from .input_cleaner.pipeline import process
+
+__all__ = ["process"]

input_cleaner-0.1.0/input_cleaner/cleaner.py

@@ -0,0 +1,182 @@
+# cleaner.py
+import re
+import math
+from collections import Counter
+
+# CONFIG PANEL
+ALLOWED = r",\.\?\(\)\/\-\+\"=<>\:@%#"
+
+CONFIG = {
+    # Normalization
+    "lowercase": True,
+    "replace_semicolon": True,
+    "replace_quotes": True,
+
+    # Duplicates
+    "remove_duplicate_words": True,
+
+    # Repeats
+    "max_char_repetition": 3,
+
+    # Heuristics
+    "enable_noise_filter": True,
+    "min_word_length": 10,
+
+    # Metrics
+    "diversity_threshold": 0.45,
+    "entropy_threshold": 3.5,
+    "min_vowel_ratio": 0.2,
+
+    # Suspicious patterns
+    "keyboard_patterns": ["qwerty", "asdf", "zxcv"],
+    "weird_bigrams": ["jh", "kj", "zx", "qk", "wk"],
+
+    # Scoring
+    "score_threshold": 2,
+
+    # Action
+    "truncate_noise": True,
+    "truncate_length": 8,
+
+    # Artificial lists
+    "max_commas": 5,
+
+    # Final cleanup
+    "collapse_symbols": True,
+    "normalize_spaces": True,
+}
+
+
+# METRICS
+def entropy(p):
+    freq = Counter(p)
+    n = len(p)
+    return -sum((c/n) * math.log2(c/n) for c in freq.values())
+
+
+def vowel_ratio(p):
+    vowels = re.findall(r'[aeiouáéíóú]', p)
+    return len(vowels) / len(p) if p else 0
+
+
+# NOISE CLASSIFIER
+def noise_score(p, cfg):
+    score = 0
+
+    if len(p) < cfg["min_word_length"]:
+        return 0
+
+    if any(c.isdigit() for c in p):
+        return 0
+
+    # Diversity
+    diversity = len(set(p)) / len(p)
+    if diversity < cfg["diversity_threshold"]:
+        score += 1
+
+    # High entropy (randomness)
+    if entropy(p) > cfg["entropy_threshold"]:
+        score += 1
+
+    # Low vowels
+    if vowel_ratio(p) < cfg["min_vowel_ratio"]:
+        score += 1
+
+    # Structural repeats
+    if re.search(r'(.{2,4})\1{2,}', p):
+        score += 1
+
+    # Keyboard patterns
+    if any(x in p for x in cfg["keyboard_patterns"]):
+        score += 1
+
+    # Weird bigrams
+    if any(bg in p for bg in cfg["weird_bigrams"]):
+        score += 1
+
+    return score
+
+
+def reduce_if_noise(match, cfg):
+    p = match.group(0)
+    score = noise_score(p, cfg)
+
+    if score >= cfg["score_threshold"]:
+        if cfg["truncate_noise"]:
+            return p[:cfg["truncate_length"]]
+        return ""
+
+    return p
+
+
+# MAIN FILTER
+def filter_input(text: str) -> str:
+    cfg = CONFIG
+
+    # Normalization
+    if cfg["lowercase"]:
+        text = text.lower()
+
+    if cfg["replace_semicolon"]:
+        text = text.replace(";", ",")
+
+    if cfg["replace_quotes"]:
+        text = text.replace("'", '"')
+
+    text = re.sub(r'[\[\{]', '(', text)
+    text = re.sub(r'[\]\}]', ')', text)
+
+    # Base filter
+    text = re.sub(
+        rf'[^a-záéíóúñüäëïöâêîôûàèìòù0-9\s{ALLOWED}]',
+        '',
+        text
+    )
+
+    # Duplicates
+    if cfg["remove_duplicate_words"]:
+        text = re.sub(r'\b(\w+)([\s.,]+\1\b)+', r'\1', text)
+
+    # Repeats
+    text = re.sub(
+        rf'(.)\1{{{cfg["max_char_repetition"]},}}',
+        r'\1',
+        text
+    )
+
+    # Weird patterns
+    text = re.sub(
+        r'([<>\W])([a-z0-9])(?:\1\2){2,}',
+        r'\2',
+        text
+    )
+
+    # Advanced heuristic
+    if cfg["enable_noise_filter"]:
+        text = re.sub(
+            r'\b[a-záéíóúñüäëïöâêîôûàèìòù]{%d,}\b' % cfg["min_word_length"],
+            lambda m: reduce_if_noise(m, cfg),
+            text
+        )
+
+    # Artificial lists
+    if text.count(",") > cfg["max_commas"]:
+        text = re.sub(
+            r'\b([a-z0-9])(?:,[a-z0-9]){3,}\b',
+            r'\1',
+            text
+        )
+
+    # Collapse symbols
+    if cfg["collapse_symbols"]:
+        text = re.sub(
+            rf'([{ALLOWED}])(\s*[{ALLOWED}])+',
+            r'\1',
+            text
+        )
+
+    # Spaces
+    if cfg["normalize_spaces"]:
+        text = re.sub(r'\s+', ' ', text).strip()
+
+    return text

input_cleaner-0.1.0/input_cleaner/compressor.py

@@ -0,0 +1,94 @@
+# Compressor.py
+
+import re
+
+# 🔹 CONFIG
+ALWAYS_REMOVE = {
+    # chat noise
+    "hello", "hey", "ok", "alright", "well",
+    "thanks", "please", "pls",
+
+    # articles
+    "the", "a", "an", "some"
+}
+
+OPTIONAL_REMOVE = {
+    # weak verbs
+    "need", "want", "wish", "can", "could",
+    "would", "like",
+
+    # prepositions
+    "of", "from", "to", "in", "on", "by", "for", "with", "without",
+
+    # pronouns
+    "me", "you", "him", "her", "us", "them", "it",
+
+    # intensifiers
+    "very", "much", "quite", "really", "super"
+}
+
+KEEP_ALWAYS = {
+    # negations
+    "no", "never",
+
+    # comparators
+    "more", "less", "better", "worse",
+
+    # logical connectors
+    "but", "because", "although", "if", "then",
+
+    # references
+    "this", "that", "those", "same"
+}
+
+
+# COMPRESSOR
+def compress_input(text: str) -> str:
+    if not text:
+        return ""
+
+    text = text.lower()
+
+    # remove consecutive duplicates
+    text = re.sub(r'\b(\w+)(\s+\1\b)+', r'\1', text)
+
+    words = text.split()
+    result = []
+
+    for w in words:
+
+        # KEEP_ALWAYS → always keep
+        if w in KEEP_ALWAYS:
+            result.append(w)
+            continue
+
+        # ALWAYS_REMOVE → always drop
+        if w in ALWAYS_REMOVE:
+            continue
+
+        # STRUCTURED DATA
+        if any(c.isdigit() for c in w):
+            result.append(w)
+            continue
+
+        # VERY SHORT WORDS
+        if len(w) < 3:
+            continue
+
+        # REPEATED PATTERNS (noise)
+        if re.search(r'(.{2,3})\1{2,}', w):
+            continue
+
+        # OPTIONAL_REMOVE
+        if w in OPTIONAL_REMOVE:
+            # drop only if enough context
+            if len(words) > 3:
+                continue
+            else:
+                result.append(w)
+                continue
+
+        # DEFAULT → keep
+        result.append(w)
+
+    return " ".join(result)

input_cleaner-0.1.0/input_cleaner/decision.py

@@ -0,0 +1,38 @@
+# decision.py
+
+def decide_input(text: str, score: float):
+
+    if not text:
+        return None, "blocked_empty"
+
+    words = text.split()
+    word_count = len(words)
+    length = len(text)
+
+    # HARD BLOCK
+    if score < 40:
+        return None, "blocked_low_score"
+
+    # typical noise (random strings)
+    if word_count == 1 and length > 12:
+        return None, "blocked_noise"
+
+    # too short input (low value)
+    if word_count <= 1 and length < 4:
+        return None, "blocked_low_info"
+
+    # SHORT USEFUL TEXT (KEEP)
+    if word_count <= 4 and score >= 70:
+        return text, "accepted_short"
+
+    # NEED COMPRESSION
+    if score < 80:
+        return text, "compress"
+
+    # LONG TEXT → SMART TRIM
+    if length > 180 or word_count > 30:
+        useful_words = words[:40]
+        return " ".join(useful_words), "truncated_smart"
+
+    # ACCEPTED
+    return text, "accepted"

input_cleaner-0.1.0/input_cleaner/pipeline.py

@@ -0,0 +1,36 @@
+# pipeline.py
+
+from .cleaner import filter_input
+from .scorer import score_input
+from .decision import decide_input
+from .compressor import compress_input
+import tiktoken
+
+
+def process(text: str):
+    original = text
+
+    cleaned = filter_input(original)
+    compressed = compress_input(cleaned)
+
+    score = score_input(cleaned)
+
+    output, status = decide_input(compressed, score)
+
+    # tiktoken (measure token reduction)
+    enc = tiktoken.encoding_for_model("gpt-4o-mini")  # or your model
+    tokens_before = len(enc.encode(original))
+    tokens_after = len(enc.encode(output)) if output else 0
+
+    return {
+        "original": original,
+        "cleaned": cleaned,
+        "compressed": compressed,
+        "score": score,
+        "status": status,
+        "output": output,
+        "token_reduction": (
+            1 - (tokens_after / tokens_before)
+            if tokens_before > 0 else 0
+        )
+    }

input_cleaner-0.1.0/input_cleaner/scorer.py

@@ -0,0 +1,125 @@
+# scorer.py
+
+import re
+import math
+from collections import Counter
+
+# CONFIG
+VOWELS = "aeiou"
+
+COMMON_BIGRAMS = {
+    "th", "he", "in", "er", "an", "re", "on", "at", "en",
+    "nd", "ti", "es", "or", "te", "of", "ed", "is", "it",
+    "al", "ar", "st", "to", "nt", "ng", "se", "ha", "as"
+}
+
+
+# METRICS
+def entropy(text):
+    freq = Counter(text)
+    n = len(text)
+    return -sum((c/n) * math.log2(c/n) for c in freq.values())
+
+
+def common_bigram_ratio(text):
+    if len(text) < 4:
+        return 1
+
+    total = 0
+    common = 0
+
+    for i in range(len(text) - 1):
+        bg = text[i:i+2]
+        total += 1
+        if bg in COMMON_BIGRAMS:
+            common += 1
+
+    return common / total if total else 1
+
+
+def max_consonant_run(text):
+    max_count = 0
+    count = 0
+
+    for c in text:
+        if c not in VOWELS and c.isalpha():
+            count += 1
+            max_count = max(max_count, count)
+        else:
+            count = 0
+
+    return max_count
+
+
+# MAIN SCORER
+def score_input(text: str) -> float:
+    if not text:
+        return 0
+
+    text = text.lower()
+    score = 100
+    words = text.split()
+
+    # structural redundancy
+    if len(words) >= 4:
+        ratio = len(set(words)) / len(words)
+        if ratio < 0.5:
+            score -= 20
+
+    # info density
+    if words:
+        avg_len = sum(len(w) for w in words) / len(words)
+        if avg_len < 3:
+            score -= 15
+
+    # entropy (more aggressive)
+    if len(text) > 12:
+        e = entropy(text)
+        if e > 4.2:
+            score -= 35
+
+    # repeated patterns
+    if re.search(r'(.{2,3})\1{2,}', text):
+        score -= 40
+
+    # consonant runs (key)
+    if max_consonant_run(text) >= 5:
+        score -= 40
+
+    # low vowel ratio per word
+    for w in words:
+        if len(w) >= 6:
+            vowels = sum(1 for c in w if c in VOWELS)
+            if vowels / len(w) < 0.25:
+                score -= 25
+                break
+
+    # suspicious single word (very key)
+    if len(words) == 1 and len(text) > 8:
+        diversity = len(set(text)) / len(text)
+        e = entropy(text)
+
+        if diversity > 0.6 and e > 3.5:
+            score -= 60
+
+    # unlikely bigrams
+    if len(text) > 10:
+        ratio_bg = common_bigram_ratio(text)
+        if ratio_bg < 0.15:
+            score -= 50
+
+    # bonus: useful density
+    if any(c.isdigit() for c in text):
+        score += 5
+
+    if 2 <= len(words) <= 6:
+        score += 5
+
+    # long redundancy
+    if len(text) > 150 and len(words) > 10:
+        ratio = len(set(words)) / len(words)
+        if ratio < 0.6:
+            score -= 15
+
+    # FINAL CLAMP
+    return max(min(score, 100), 0)

input_cleaner-0.1.0/input_cleaner.egg-info/PKG-INFO

@@ -0,0 +1,177 @@
+Metadata-Version: 2.4
+Name: input_cleaner
+Version: 0.1.0
+Summary: Text cleaning, scoring and compression pipeline
+Author: marlon(MARLM8)
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tiktoken
+Dynamic: license-file
+
+# Input Cleaner
+
+Lightweight text preprocessing pipeline for cleaning, scoring and compressing user input.
+
+Designed for LLM optimization, noise reduction and token efficiency.
+
+---
+
+## Features
+
+* Text normalization and cleanup
+* Noise detection using heuristic scoring
+* Input compression (removes low-value words)
+* Quality scoring system (0–100)
+* Smart truncation for long inputs
+* Token reduction tracking using `tiktoken`
+
+---
+
+## Installation
+
+```bash
+pip install input_cleaner
+```
+
+Or local development:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick Start
+
+```python
+from input_cleaner import process
+
+result = process("hello hello I really really need help with this")
+
+print(result)
+```
+
+---
+
+## Example Output
+
+```json
+{
+  "original": "hello hello I really really need help with this",
+  "cleaned": "hello i really need help with this",
+  "compressed": "need help this",
+  "score": 78,
+  "status": "compress",
+  "output": "need help this",
+  "token_reduction": 0.32
+}
+```
+
+---
+
+## Pipeline Overview
+
+The system processes text in 4 stages:
+
+1. **Cleaning**
+
+   * Normalize text (lowercase, symbols)
+   * Remove duplicates and noise patterns
+
+2. **Compression**
+
+   * Remove weak or redundant words
+   * Preserve important tokens
+
+3. **Scoring**
+
+   * Evaluate text quality using:
+
+     * entropy
+     * character diversity
+     * vowel ratio
+     * pattern detection
+
+4. **Decision**
+
+   * Block low-quality input
+   * Compress medium-quality input
+   * Accept high-quality input
+   * Truncate long input if needed
+
+---
+
+## Status Values
+
+| Status              | Meaning               |
+| ------------------- | --------------------- |
+| `blocked_empty`     | Empty input           |
+| `blocked_low_score` | Low quality score     |
+| `blocked_noise`     | Likely random string  |
+| `blocked_low_info`  | Too short / low value |
+| `accepted_short`    | Short but valid       |
+| `compress`          | Needs compression     |
+| `truncated_smart`   | Long input trimmed    |
+| `accepted`          | Fully valid           |
+
+---
+
+## Use Cases
+
+* Preprocessing user input for LLMs
+* Reducing token costs
+* Filtering spam or noisy text
+* Improving prompt quality
+* Input validation layer for APIs
+
+---
+
+## Requirements
+
+* Python 3.8+
+* `tiktoken`
+
+---
+
+## Project Structure
+
+```bash
+text_pipeline/
+├── cleaner.py
+├── compressor.py
+├── scorer.py
+├── decision.py
+└── pipeline.py
+```
+
+---
+
+## Design Goals
+
+* Fast (pure Python, no heavy dependencies)
+* Deterministic (no randomness)
+* Modular (each step isolated)
+* Easy to extend
+
+---
+
+## Roadmap 
+
+* Add trigram scoring
+* Language detection
+* Configurable thresholds
+* FastAPI wrapper
+* Streaming support
+
+---
+
+## License
+
+Apache-2.0
+
+---
+
+## Author
+
+marlon (MARLM8)

input_cleaner-0.1.0/input_cleaner.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+input_cleaner/__init__.py
+input_cleaner/cleaner.py
+input_cleaner/compressor.py
+input_cleaner/decision.py
+input_cleaner/pipeline.py
+input_cleaner/scorer.py
+input_cleaner.egg-info/PKG-INFO
+input_cleaner.egg-info/SOURCES.txt
+input_cleaner.egg-info/dependency_links.txt
+input_cleaner.egg-info/requires.txt
+input_cleaner.egg-info/top_level.txt
+tests/test.py

input_cleaner-0.1.0/input_cleaner.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

input_cleaner-0.1.0/input_cleaner.egg-info/requires.txt

@@ -0,0 +1 @@
+tiktoken

input_cleaner-0.1.0/input_cleaner.egg-info/top_level.txt

@@ -0,0 +1 @@
+input_cleaner

input_cleaner-0.1.0/pyproject.toml

@@ -0,0 +1,17 @@
+[project]
+name = "input_cleaner"
+version = "0.1.0"
+description = "Text cleaning, scoring and compression pipeline"
+authors = [
+    {name = "marlon(MARLM8)"}
+]
+readme = "README.md"
+requires-python = ">=3.8"
+
+dependencies = [
+    "tiktoken"
+]
+
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

input_cleaner-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

input_cleaner-0.1.0/tests/test.py

@@ -0,0 +1,8 @@
+from input_cleaner import process
+
+while True:
+    user_input = input(" enter your text: ")
+    if user_input.lower() == "exit":
+        break
+    result = process(user_input)
+    print(result)