from typing import Optional

TASKS_PRETTY = {
    "library_based_code_generation": "Library-based code generation",
    "ci_builds_repair": "CI builds repair",
    "project_code_completion": "Project-level code completion",
    "commit_message_generation": "Commit message generation",
    "bug_localization": "Bug localization",
    "module_summarization": "Module Summarization",
}
TASKS_PRETTY_REVERSE = {value: key for key, value in TASKS_PRETTY.items()}

TASKS_DESCRIPTIONS = {
    "library_based_code_generation": """# Library-Based Code Generation\n
        
        Our Library-Based Code Generation benchmark 🤗 [JetBrains-Research/lca-library-based-code-generation](https://huggingface.co/datasets/JetBrains-Research/lca-library-based-code-generation) includes 150 manually curated instructions asking model to generate Python code using a particular library. Samples come from 62 Python repositories. All the samples in the dataset are based on reference example programs written by authors of the respective libraries.
        
        For evaluation we use two metrics:
        * `API Recall`: share of library-specific API calls used in the reference program that appear in the generated code,  
        * `ChrF`: textual similarity between the generated code and the reference program.  

        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `library_based_code_generation` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
        """,

    "ci_builds_repair": """# CI Builds Repair\n
        
        Our CI Builds Repair benchmark 🤗 [JetBrains-Research/lca-ci-builds-repair](https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair) includes 77 data points.

        We use Pass@1 metric for CI repair.
        We evaluate Exact Match for different line categories:

        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `ci-builds-repair` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint.
        """,

    "project_code_completion": """# Project-Level Code Completion\n
        
        Our Project-Level Code Completion benchmark 🤗 [JetBrains-Research/lca-project-level-code-completion](https://huggingface.co/datasets/JetBrains-Research/lca-project-level-code-completion) includes four datasets:
        * `small-context`: 144 data points,
        * `medium-context`: 224 data points,
        * `large-context`: 270 data points,
        * `huge-context`: 296 data points.

        We use standard Exact Match (EM) metric for one-line code completion.
        We evaluate Exact Match for different line categories:
        * *infile* – functions and classes are from the completion file;
        * *inproject* – functions and files are from the repository snapshot;
        * *committed* – functions and classes are from the files that were added on the completion file commit;
        * *common* – functions and classes with common names, e.g., `main`, `get`, etc.;
        * *non-informative* – short/long lines, import/print lines, or comment lines;
        * *random* – lines that doesn't fit to any of previous categories.

        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `code_completion` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
        """,

    "commit_message_generation": """# Commit Message Generation\n
        
        Our Commit Message Generation benchmark 🤗 [JetBrains-Research/lca-commit-message-generation](https://huggingface.co/datasets/JetBrains-Research/lca-commit-message-generation) includes 163 manually curated commits from Python projects.  
        
        We use the following metrics for evaluation:
        * [BLEU](https://huggingface.co/spaces/evaluate-metric/sacrebleu)
        * [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge)
        * [ChrF](https://huggingface.co/spaces/evaluate-metric/chrf)
        * [BERTScore](https://huggingface.co/spaces/evaluate-metric/bertscore)
        
        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `commit_message_generation` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
        
        **Note.** The leaderboard is sorted by ROUGE-1 metric by default.       
        """,

    "bug_localization": """# Bug Localization\n
        
        Our Module-to-Text benchmark 🤗 [JetBrains-Research/lca-bug-localization](https://huggingface.co/datasets/JetBrains-Research/lca-bug-localization) includes 7,479 bug issue descriptions with information about pull request that fix them for Python, Java and Kotlin projects. 
        
        Moreover, 150 data points from the test split were manually verified and can be used for bug localization approaches evaluation.
        We used information retrieval metrics such as R@k, P@k and F1-score for evaluation, taking k equal to 1 and 2.
    """,

    "module_summarization": """# Module Summarization\n
        Our Module Summarization benchmark 🤗 [JetBrains-Research/lca-module-summarization](https://huggingface.co/datasets/JetBrains-Research/lca-module-summarization) includes 216 manually curated text files describing different documentation of opensource permissive Python projects. 

        We use new metric for evaluation:
        * `CompScore`: New metric proposed for this task. More details in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines/blob/main/module_summarization/README.md)

        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `module_summarization` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines/blob/main/module_summarization/).
        """,
}


def get_submission_text_files_for_task(task_pretty: Optional[str]) -> str:
    if not task_pretty:
        return "Please, select a specific task to see more detailed instructions regarding submitting files."

    task_id = TASKS_PRETTY_REVERSE[task_pretty]

    if task_id == "commit_message_generation":
        return f"""**{task_pretty} Instructions:**\n\n* Please, attach files in [JSONLines format](https://jsonlines.org/). For an example, check the predictions provided by 🏟️ Long Code Arena Team in  🤗 [JetBrains-Research/lca-results](https://huggingface.co/datasets/JetBrains-Research/lca-results/tree/main/commit_message_generation/predictions). Make sure to include `"prediction"` and `"reference"` fields for each example, the rest are optional."""

    return f"**{task_pretty} Instructions:**\n\n* 🚧 There are no instructions for the current task yet."