QuiCommit/src/llm/parsing.rs

use anyhow::{Result, bail};

/// Parse commit response from LLM
pub(crate) fn parse_commit_response(
    response: &str,
    format: crate::config::CommitFormat,
) -> Result<GeneratedCommit> {
    // Clean markdown code fences from the response
    let cleaned = strip_code_fences(response);

    let lines: Vec<&str> = cleaned
        .lines()
        .map(|l| l.trim())
        .filter(|l| !l.is_empty())
        .collect();

    if lines.is_empty() {
        let preview: String = response.chars().take(200).collect();
        bail!(
            "LLM returned empty or whitespace-only response. \
             Raw response preview: '{}'. \
             Hint: If using DeepSeek/Kimi with thinking enabled, \
             the model may have returned reasoning_content only. \
             Try disabling thinking mode or switching models.",
            preview
        );
    }

    // Find the line most likely to be the commit subject
    let first_line = find_commit_subject_line(&lines, format);

    // Parse based on format
    match format {
        crate::config::CommitFormat::Conventional => {
            parse_conventional_commit(first_line, &lines, response)
        }
        crate::config::CommitFormat::Commitlint => {
            parse_commitlint_commit(first_line, &lines, response)
        }
    }
}

/// Remove surrounding markdown code fences (```) from LLM output
fn strip_code_fences(response: &str) -> String {
    let mut lines: Vec<&str> = response.lines().collect();

    // Strip leading fence lines (``` or ```lang)
    while lines.first().map_or(false, |l| l.trim().starts_with("```")) {
        lines.remove(0);
    }

    // Strip trailing fence lines
    while lines.last().map_or(false, |l| l.trim() == "```") {
        lines.pop();
    }

    lines.join("\n")
}

/// Find the line that is most likely the commit subject among extracted lines
fn find_commit_subject_line<'a>(
    lines: &[&'a str],
    format: crate::config::CommitFormat,
) -> &'a str {
    let valid_types = crate::utils::validators::get_commit_types(matches!(
        format,
        crate::config::CommitFormat::Commitlint
    ));

    // First pass: line starting with a known type that also has proper syntax
    // (e.g. "type:", "type(scope):", "type!:")
    for &line in lines {
        let trimmed = line.trim();
        for &t in valid_types {
            if let Some(rest) = trimmed.strip_prefix(t) {
                if rest.starts_with(':') || rest.starts_with('(') || rest.starts_with("!:") {
                    return trimmed;
                }
            }
        }
    }

    // Second pass: any line containing a colon (generic "prefix: description")
    for &line in lines {
        if line.contains(':') {
            return line.trim();
        }
    }

    // Fallback: return the first line as-is
    lines[0].trim()
}

fn parse_conventional_commit(
    first_line: &str,
    lines: &[&str],
    raw_response: &str,
) -> Result<GeneratedCommit> {
    // Parse: type(scope)!: description
    let parts: Vec<&str> = first_line.splitn(2, ':').collect();
    if parts.len() != 2 {
        let preview: String = raw_response.chars().take(300).collect();
        bail!(
            "Invalid conventional commit format: missing colon.\n\
             Parsed subject line: '{}'\n\
             Raw response preview: '{}'\n\
             Expected: <type>[optional scope]: <description>",
            first_line,
            preview
        );
    }

    let type_part = parts[0];
    let description = parts[1].trim();

    // Extract type, scope, and breaking indicator
    let breaking = type_part.ends_with('!');
    let type_part = type_part.trim_end_matches('!');

    let (commit_type, scope) = if let Some(start) = type_part.find('(') {
        if let Some(end) = type_part.find(')') {
            let t = &type_part[..start];
            let s = &type_part[start + 1..end];
            (t.to_string(), Some(s.to_string()))
        } else {
            bail!("Invalid scope format: missing closing parenthesis");
        }
    } else {
        (type_part.to_string(), None)
    };

    // Extract body and footer
    let (body, footer) = extract_body_footer(lines);

    Ok(GeneratedCommit {
        commit_type,
        scope,
        description: description.to_string(),
        body,
        footer,
        breaking,
    })
}

fn parse_commitlint_commit(
    first_line: &str,
    lines: &[&str],
    raw_response: &str,
) -> Result<GeneratedCommit> {
    // Similar parsing but with commitlint rules
    let parts: Vec<&str> = first_line.splitn(2, ':').collect();
    if parts.len() != 2 {
        let preview: String = raw_response.chars().take(300).collect();
        bail!(
            "Invalid commit format: missing colon.\n\
             Parsed subject line: '{}'\n\
             Raw response preview: '{}'\n\
             Expected: <type>[optional scope]: <subject>",
            first_line,
            preview
        );
    }

    let type_part = parts[0];
    let subject = parts[1].trim();

    let (commit_type, scope) = if let Some(start) = type_part.find('(') {
        if let Some(end) = type_part.find(')') {
            let t = &type_part[..start];
            let s = &type_part[start + 1..end];
            (t.to_string(), Some(s.to_string()))
        } else {
            (type_part.to_string(), None)
        }
    } else {
        (type_part.to_string(), None)
    };

    let (body, footer) = extract_body_footer(&lines);

    Ok(GeneratedCommit {
        commit_type,
        scope,
        description: subject.to_string(),
        body,
        footer,
        breaking: false,
    })
}

fn extract_body_footer(lines: &[&str]) -> (Option<String>, Option<String>) {
    if lines.len() <= 1 {
        return (None, None);
    }

    let rest: Vec<&str> = lines[1..]
        .iter()
        .skip_while(|l| l.trim().is_empty())
        .copied()
        .collect();

    if rest.is_empty() {
        return (None, None);
    }

    // Look for footer markers
    let footer_markers = [
        "BREAKING CHANGE:",
        "Closes",
        "Fixes",
        "Refs",
        "Co-authored-by:",
    ];

    let mut body_lines = vec![];
    let mut footer_lines = vec![];
    let mut in_footer = false;

    for line in &rest {
        if footer_markers.iter().any(|m| line.starts_with(m)) {
            in_footer = true;
        }

        if in_footer {
            footer_lines.push(*line);
        } else {
            body_lines.push(*line);
        }
    }

    let body = if body_lines.is_empty() {
        None
    } else {
        Some(body_lines.join("\n"))
    };

    let footer = if footer_lines.is_empty() {
        None
    } else {
        Some(footer_lines.join("\n"))
    };

    (body, footer)
}

/// Generated commit structure
#[derive(Debug, Clone)]
pub struct GeneratedCommit {
    pub commit_type: String,
    pub scope: Option<String>,
    pub description: String,
    pub body: Option<String>,
    pub footer: Option<String>,
    pub breaking: bool,
}

impl GeneratedCommit {
    /// Format as conventional commit
    pub fn to_conventional(&self) -> String {
        crate::utils::formatter::format_conventional_commit(
            &self.commit_type,
            self.scope.as_deref(),
            &self.description,
            self.body.as_deref(),
            self.footer.as_deref(),
            self.breaking,
        )
    }

    /// Format as commitlint commit
    pub fn to_commitlint(&self) -> String {
        crate::utils::formatter::format_commitlint_commit(
            &self.commit_type,
            self.scope.as_deref(),
            &self.description,
            self.body.as_deref(),
            self.footer.as_deref(),
            None,
        )
    }
}