Advanced mq Techniques: From Simple Queries to Complex Workflows

# Extract different content based on header level
mq 'let text = to_text(self)
    | if (is_h1()):
      s"# Table of Contents for ${text}"
    elif (is_h2()):
      s"## ${text}"
    else:
      None' documentation.md

# Find code blocks that contain specific patterns
mq '.code | select(or(contains("async"), contains("function")))' api-docs.md

# Extract headers that don't contain "deprecated"
mq '.h | select(not(contains("deprecated")))' changelog.md

# Find lists with more than 3 items
mq '.[] | select(len() > 3)' requirements.md

# Define reusable values
mq -I null 'let project_name = "my-awesome-project" |
    let version = "1.0.0" |
    s"# ${project_name} v${version}\n\nWelcome to ${project_name}!"'

# Generate badges dynamically
mq -I null 'let lang = "rust" |
    let repo = "harehare/mq" |
    s"[![${lang}](https://img.shields.io/badge/language-${lang}-orange.svg)](https://github.com/${repo})"'

# Process all markdown files in a directory
mq '.h1 | to_text()' docs/**/*.md

# Combine multiple files with separators
mq -S 's"\n---\n# ${__FILE__}\n---\n"' 'identity()' docs/*.md

# Extract code examples from all files
mq '.code("javascript") | to_text()' tutorials/**/*.md

# Add file context to extracted content
mq 'let filename = __FILE__
    | let text = to_text(self)
    | .code
    | s"From ${filename}:\n${text}\n"' examples/*.md

# Generate API documentation index
mq 'select(.h2) |
    let title = to_text(self) |
    let anchor = to_link(s"#${title}", title, "") |
    to_md_list(anchor, 1)' api/*.md > api-index.md

# Convert HTML to Markdown and extract specific sections
mq 'select(or(.h1, .h2))
  | let text = to_text(self)
  | if (is_h1()):
      s"# ${text}"
    else:
      s"## ${text}"' legacy-docs.html

# Extract code examples for training data
mq '.code |
    let code_content = to_text(self) |
    s"Code:\n${code_content}\n---"' tutorials/*.md

# Prepare content for embedding
mq 'select(or(.h, .text)) |
    let type = to_md_name() |
    let content = to_text(self) |
    s"${type}: ${content}"' knowledge-base/*.md

# Convert CSV data to markdown tables
mq 'nodes | csv2table_with_header()' data.csv

def format_api_endpoint(method, path, description):
  s"**${method}** `${path}`\n\n${description}\n";

def extract_endpoints():
  select(or(select(starts_with("GET"), starts_with("POST"))));

mq 'include "custom" | .code | extract_endpoints() | format_api_endpoint("GET", self, "API endpoint")' api-docs.md

# Process large numbers of files in parallel
mq -P 5 '.h1 | to_text()' docs/**/*.md

# Process large files without loading everything into memory
mq --unbuffered '.code | to_text()' large-documentation.md

# GitHub Actions example
- name: Extract API Changes
  run: |
    mq 'select(and(.h2, contains("API"))) | to_text()' CHANGELOG.md > api-changes.txt

# Extract version from changelog
VERSION=$(mq 'select(.h2) | to_text() | match("v?([0-9.]+)")' CHANGELOG.md)
echo "Building version: $VERSION"

# Find outdated documentation sections
mq 'select(or(contains("TODO"), contains("FIXME")))
    | s"File: ${__FILE__}\nIssue: ${to_text(self)}"' docs/**/*.md

# Check for broken internal links
mq '.link | select(starts_with("#")) |
    let target = slice(1) |
    s"Link target: ${target}"' *.md