Add Readme and code for Document localisation, OCR, SLID, Text analysis

python/document-localization/README.md

@@ -0,0 +1,86 @@
+# Reverie Language Translation API Example
+
+This is a simple Python script demonstrating how to use the Reverie Language Translation API to upload, translate, and download documents.
+
+## Prerequisites
+
+* **Python 3.6+:** Ensure you have Python installed on your system.
+* **Required Libraries:** Install the necessary libraries using pip:
+
+    ```bash
+    pip install requests
+    ```
+
+* **Reverie API Credentials:** You will need a Reverie API key, application ID, and application name. Obtain these from your Reverie developer account.
+
+## Setup
+
+1.  **Clone or Download:** Clone this repository or download the Python script (`your_script_name.py`).
+2.  **API Credentials:** Replace the placeholder API credentials in the script with your actual credentials:
+
+    ```python
+    REV_APP_ID = "your_app_id"  # Replace with your Reverie App ID
+    REV_APPNAME = "your_app_name" # Replace with your Reverie App Name
+    REV_API_KEY = "your_api_key"  # Replace with your Reverie API Key
+    ```
+
+3.  **Input File:** Place the document you want to translate (e.g., a `.pdf` or `.docx` file) in the same directory as the script. Change the `file_path` variable in the script to the name of your file.
+
+    ```python
+    file_path = 'your_document.pdf' # Replace with your file name
+    ```
+
+4.  **Source and Target Languages:** Specify the source and target languages. The supported languages are:
+
+    * english
+    * bengali
+    * gujarati
+    * hindi
+    * kannada
+    * malayalam
+    * odia
+    * punjabi
+    * sanskrit
+    * tamil
+    * telugu
+
+    Change the `source_lang` and `target_lang` variables in the script:
+
+    ```python
+    source_lang = 'english'  # Source language (e.g., English)
+    target_lang = 'hindi'  # Target language (e.g., Hindi)
+    ```
+
+## Running the Script
+
+1.  **Open a Terminal or Command Prompt:** Navigate to the directory containing the script.
+2.  **Execute the Script:** Run the Python script:
+
+    ```bash
+    python your_script_name.py
+    ```
+
+3.  **Output:** The script will:
+    * Upload the file to the Reverie API.
+    * Check the translation status periodically.
+    * Download the translated document to the `output` directory.
+    * Print status messages to the console.
+
+4.  **Translated Document:** The translated document will be saved in the `output` directory as `translated_document_{target_lang}.docx`.
+
+## Example Usage
+
+To translate a file named `my_document.pdf` from English to Tamil:
+
+1.  Place `my_document.pdf` in the same directory as the script.
+2.  Set `file_path = 'my_document.pdf'`, `source_lang = 'en'`, and `target_lang = 'ta'`.
+3.  Run the script: `python your_script_name.py`.
+4.  The translated document will be saved as `output/translated_document_ta.docx`.
+
+## Important Notes
+
+* Ensure you have a stable internet connection.
+* The translation time depends on the size of the document and the Reverie API's processing load.
+* If you encounter any errors, check the console output for error messages.
+* Ensure your API keys are correct.
+* This example is for educational purpose, for production environment, please handle exceptions and errors properly.

python/document-localization/main.py

@@ -0,0 +1,107 @@
+import os
+import time
+import requests
+
+REV_APP_ID = "<YOUR-APP-ID>"
+REV_APPNAME = "nmt"
+REV_API_KEY = "<YOUR-API-KEY>"
+
+UPLOAD_URL = "https://revapi.reverieinc.com/translate_doc_import"
+STATUS_URL = "https://revapi.reverieinc.com/translate_doc_status"
+DOWNLOAD_URL = "https://revapi.reverieinc.com/translate_doc_export"
+
+OUTPUT_DIR = "output"
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+def upload_file(file_path, source_lang, target_lang):
+    """Uploads a document for translation."""
+    with open(file_path, "rb") as file:
+        files = {"projectFiles": file}
+        data = {"sourceLanguage": source_lang, "targetLanguage": target_lang}
+        headers = {
+            "REV-APP-ID": REV_APP_ID,
+            "REV-APPNAME": REV_APPNAME,
+            "REV-API-KEY": REV_API_KEY,
+        }
+
+        response = requests.post(UPLOAD_URL, headers=headers, files=files, data=data)
+        if response.status_code == 200:
+            json_response = response.json()
+            print("File uploaded successfully.")
+            return json_response.get("projectId")
+        else:
+            print("Error in uploading file:", response.text)
+            return None
+
+def check_status(doc_id):
+    """Checks the translation status."""
+    while True:
+        params = {"doc_id": doc_id}
+        headers = {
+            "REV-APP-ID": REV_APP_ID,
+            "REV-APPNAME": REV_APPNAME,
+            "REV-API-KEY": REV_API_KEY,
+        }
+
+        response = requests.get(STATUS_URL, headers=headers, params=params)
+        json_response = response.json()
+
+        if json_response.get("success") and json_response.get("message") == "completed":
+            print("Translation completed!")
+            return True
+        else:
+            print("Translation in progress... Checking again in 2 seconds.")
+            time.sleep(2)
+
+def download_translation(doc_id, target_lang):
+    """Downloads the translated document and saves it to the output folder."""
+    headers = {
+        "Content-Type": "application/json",
+        "REV-APP-ID": REV_APP_ID,
+        "REV-APPNAME": REV_APPNAME,
+        "REV-API-KEY": REV_API_KEY,
+    }
+
+    json_data = {"unitId": doc_id, "targetLanguages": [target_lang]}
+    response = requests.post(DOWNLOAD_URL, headers=headers, json=json_data)
+
+    if response.status_code == 200:
+        json_response = response.json()
+        if json_response.get("success"):
+            target_urls = json_response.get("data", {}).get("targetURLS", {})
+            for filename, lang_urls in target_urls.items():
+                file_url = lang_urls.get(target_lang)
+                if file_url:
+                    download_and_save(file_url, filename)
+                    print('File downloaded successfully')
+                else:
+                    print(f"Target language '{target_lang}' not found for file '{filename}'.")
+    else:
+        print("Error downloading translation:", response.text)
+
+
+def download_and_save(file_url, filename):
+    """Downloads the file from the URL and saves it."""
+    response = requests.get(file_url, stream=True)
+
+    if response.status_code == 200:
+        output_path = os.path.join(OUTPUT_DIR, f"translated_{filename}")
+        with open(output_path, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+        print(f"Saved translated file to: {output_path}")
+    else:
+        print("Failed to download translated document.")
+
+
+if __name__ == "__main__":
+    file_path = '<YOUR-FILE-PATH>'
+    source_lang = '<SOURCE-LANGUAGE>'
+    target_lang = '<TARGET-LANGUAGE>'
+
+    doc_id = upload_file(file_path, source_lang, target_lang)
+
+    if doc_id:
+        if check_status(doc_id):
+            download_translation(doc_id, target_lang)

python/language-identification-voice/README.md

@@ -0,0 +1,47 @@
+# REVERIE LANGUAGE TECHNOLOGIES SLID API Client
+
+This Python script provides a client for interacting with the Spoken Language Identification (SLID) API. It allows you to upload an audio file and identify the spoken language.
+
+## Prerequisites
+
+* Python 3.6 or higher
+* `requests` library (Install using: `pip install requests`)
+
+## Installation
+
+1.  Clone this repository or download the `slid_api_client.py` file.
+
+## Usage
+
+1.  **Obtain API Credentials:** You need to have a valid API Key and App ID provided by Reverie. 
+2.  **Install Dependencies:** If you haven't already, install the necessary Python library:
+    ```bash
+    pip install requests
+    ```
+3.  **Configure the Script:**
+    * Open `slid_api_client.py` in a text editor.
+    * Replace `<Your API Key>` and `<Your App ID>` with your actual API credentials.
+    * Modify the `audio_file` variable to point to the path of the audio file you want to analyze.
+    * If your audio file is not in the default format (WAV, Signed 16 bit, 16,000 Hz), you can specify the format using the `audio_format` parameter in the `identify_language` function. 
+4.  **Run the Script:**
+    ```bash
+    python slid_api_client.py
+    ```
+5.  **View the Output:** The script will print the JSON response from the API, which includes the detected language and confidence score.
+
+## Code Details
+
+* The `SLIDApiClient` class encapsulates the API interaction.
+* The `identify_language` method sends a POST request to the SLID API endpoint with the audio file and necessary headers.  
+* Error handling is implemented using `try-except` blocks to catch potential exceptions during the API request.  
+* The script demonstrates how to use the client with both the default audio format and a specific format.
+
+## Supported Audio Formats
+
+The API supports various audio formats, including:  
+
+* WAV (default): Signed 16 bit, 16,000 Hz (16k\_int16), Unsigned 8 bit, 16,000 Hz (16k\_uint8),  Signed 16 bit, 8,000 Hz (8k\_int16), Unsigned 8 bit, 8,000 Hz (8k\_uint8)
+* MP3
+* FLAC
+* OGG Vorbis
+* OGG Opus

python/language-identification-voice/main.py

@@ -0,0 +1,65 @@
+import requests
+import os
+
+class SLIDApiClient:
+    def __init__(self, api_key, app_id):
+        """
+        Initializes the SLID API client.
+
+        Args:
+            api_key (str): The API key provided by Reverie.
+            app_id (str): The App ID provided by Reverie.
+        """
+        self.api_key = api_key
+        self.app_id = app_id
+        self.base_url = "https://revapi.reverieinc.com/upload"
+
+    def identify_language(self, audio_file_path, audio_format=None):
+        """
+        Identifies the language spoken in the given audio file.
+
+        Args:
+            audio_file_path (str):  Path to the audio file.
+            audio_format (str, optional): Format of the audio file. Defaults to None.
+
+        Returns:
+            dict: The JSON response from the API.
+        """
+        headers = {
+            "REV-API-KEY": self.api_key,
+            "REV-APP-ID": self.app_id,
+            "REV-APPNAME": "slid",  
+        }
+        files = {"audio_file": open(audio_file_path, "rb")}
+        data = {}
+
+        if audio_format:
+            headers["format"] = audio_format
+
+        try:
+            response = requests.post(self.base_url, headers=headers, files=files)
+            response.raise_for_status()
+            return response.json()
+        except requests.exceptions.RequestException as e:
+            print(f"Error: {e}")
+            return None
+        finally:
+            files["audio_file"].close()
+
+if __name__ == "__main__":
+    api_key = "<YOUR-API-KEY>"
+    app_id = "<YOUR-APP-ID>"
+
+    client = SLIDApiClient(api_key, app_id)
+    audio_file = "<PATH-TO-YOUR-FILE>"
+
+    result = client.identify_language(audio_file)
+    if result:
+        print("Language Identification Result:")
+        print(result)
+
+    # Example usage with a specific audio format (e.g., mp3)
+    # result_mp3 = client.identify_language(audio_file, audio_format="mp3")
+    # if result_mp3:
+    #     print("Language Identification Result (MP3):")
+    #     print(result_mp3)