docrev 0.11.2 → 0.12.0

package/lib/schema.ts

@@ -1,494 +0,0 @@
-/**
- * JSON Schema validation for rev.yaml configuration
- */
-
-/**
- * Validation error
- */
-interface ValidationError {
-  path: string;
-  message: string;
-  value?: unknown;
-}
-
-/**
- * Validation warning
- */
-interface ValidationWarning {
-  path: string;
-  message: string;
-}
-
-/**
- * Validation result
- */
-interface ValidationResult {
-  valid: boolean;
-  errors: ValidationError[];
-  warnings: ValidationWarning[];
-}
-
-/**
- * JSON Schema type
- */
-interface Schema {
-  $schema?: string;
-  title?: string;
-  description?: string;
-  type?: string;
-  properties?: Record<string, Schema>;
-  required?: string[];
-  items?: Schema;
-  oneOf?: Schema[];
-  enum?: string[];
-  pattern?: string;
-  format?: string;
-  minimum?: number;
-  maximum?: number;
-  minItems?: number;
-  maxItems?: number;
-  additionalProperties?: boolean;
-  default?: unknown;
-}
-
-/**
- * JSON Schema for rev.yaml
- */
-export const revYamlSchema: Schema = {
-  $schema: 'http://json-schema.org/draft-07/schema#',
-  title: 'rev.yaml configuration',
-  description: 'Configuration file for docrev document workflow',
-  type: 'object',
-  properties: {
-    title: {
-      type: 'string',
-      description: 'Document title',
-    },
-    version: {
-      type: 'string',
-      description: 'Document version',
-    },
-    authors: {
-      type: 'array',
-      description: 'List of authors',
-      items: {
-        oneOf: [
-          { type: 'string' },
-          {
-            type: 'object',
-            properties: {
-              name: { type: 'string' },
-              affiliation: { type: 'string' },
-              email: { type: 'string', format: 'email' },
-              orcid: { type: 'string', pattern: '^\\d{4}-\\d{4}-\\d{4}-\\d{3}[0-9X]$' },
-            },
-            required: ['name'],
-          },
-        ],
-      },
-    },
-    journal: {
-      type: 'string',
-      description: 'Journal profile name for formatting defaults and validation',
-    },
-    'pandoc-args': {
-      type: 'array',
-      description: 'Extra pandoc args applied to every format build (e.g. --lua-filter=...). Format-specific lists are appended after these; --pandoc-arg CLI values are appended last.',
-      items: { type: 'string' },
-    },
-    output: {
-      type: 'object',
-      description: 'Per-format output filenames. Keys are format names (pdf, docx, tex, beamer, pptx); values are paths. Relative paths resolve under outputDir; absolute paths are honored as-is. Extension auto-added if missing. CLI `-o` overrides this map.',
-      properties: {
-        pdf: { type: 'string' },
-        docx: { type: 'string' },
-        tex: { type: 'string' },
-        beamer: { type: 'string' },
-        pptx: { type: 'string' },
-      },
-      additionalProperties: false,
-    },
-    sections: {
-      type: 'array',
-      description: 'Ordered list of section files to include',
-      items: { type: 'string', pattern: '.*\\.md$' },
-    },
-    bibliography: {
-      type: 'string',
-      description: 'Path to bibliography file (.bib)',
-      pattern: '.*\\.bib$',
-    },
-    csl: {
-      type: 'string',
-      description: 'Path to CSL citation style file',
-    },
-    crossref: {
-      type: 'object',
-      description: 'pandoc-crossref settings',
-      properties: {
-        figureTitle: { type: 'string', default: 'Figure' },
-        tableTitle: { type: 'string', default: 'Table' },
-        figPrefix: {
-          oneOf: [
-            { type: 'string' },
-            { type: 'array', items: { type: 'string' }, minItems: 1, maxItems: 2 },
-          ],
-        },
-        tblPrefix: {
-          oneOf: [
-            { type: 'string' },
-            { type: 'array', items: { type: 'string' }, minItems: 1, maxItems: 2 },
-          ],
-        },
-        eqnPrefix: {
-          oneOf: [
-            { type: 'string' },
-            { type: 'array', items: { type: 'string' }, minItems: 1, maxItems: 2 },
-          ],
-        },
-        secPrefix: {
-          oneOf: [
-            { type: 'string' },
-            { type: 'array', items: { type: 'string' }, minItems: 1, maxItems: 2 },
-          ],
-        },
-        linkReferences: { type: 'boolean', default: true },
-      },
-      additionalProperties: true,
-    },
-    pdf: {
-      type: 'object',
-      description: 'PDF output settings',
-      properties: {
-        template: { type: 'string' },
-        documentclass: {
-          type: 'string',
-          enum: ['article', 'report', 'book', 'memoir', 'scrartcl', 'scrreprt', 'scrbook'],
-          default: 'article',
-        },
-        fontsize: {
-          type: 'string',
-          pattern: '^\\d{1,2}pt$',
-          default: '12pt',
-        },
-        geometry: { type: 'string', default: 'margin=1in' },
-        linestretch: { type: 'number', minimum: 1, maximum: 3, default: 1.5 },
-        numbersections: { type: 'boolean', default: false },
-        toc: { type: 'boolean', default: false },
-        header: {
-          type: 'string',
-          description: 'Path (relative to the project root) to a LaTeX preamble file injected via pandoc -H, e.g. a header.tex with \\usepackage{lineno}\\linenumbers or fancyhdr running headers. A missing file is reported, not silently dropped. For inline LaTeX use a top-level header-includes: block instead.',
-        },
-        footer: {
-          type: 'string',
-          description: 'Second LaTeX preamble file (relative to the project root), injected via -H after pdf.header.',
-        },
-        'pandoc-args': {
-          type: 'array',
-          description: 'Extra pandoc args for PDF builds. Appended after the top-level pandoc-args list.',
-          items: { type: 'string' },
-        },
-      },
-      additionalProperties: true,
-    },
-    docx: {
-      type: 'object',
-      description: 'Word output settings',
-      properties: {
-        reference: { type: 'string', description: 'Reference document for styling' },
-        keepComments: { type: 'boolean', default: true },
-        toc: { type: 'boolean', default: false },
-        translateRawFigures: {
-          type: 'boolean',
-          default: true,
-          description: 'Auto-translate the common \\begin{figure}...\\end{figure} shape to portable ![](){#fig: ...} markdown so figures render in docx. Pandoc strips raw LaTeX in docx output silently otherwise.',
-        },
-        'pandoc-args': {
-          type: 'array',
-          description: 'Extra pandoc args for DOCX builds. Appended after the top-level pandoc-args list.',
-          items: { type: 'string' },
-        },
-      },
-      additionalProperties: true,
-    },
-    tex: {
-      type: 'object',
-      description: 'LaTeX output settings',
-      properties: {
-        standalone: { type: 'boolean', default: true },
-        'pandoc-args': {
-          type: 'array',
-          description: 'Extra pandoc args for TeX builds. Appended after the top-level pandoc-args list.',
-          items: { type: 'string' },
-        },
-      },
-      additionalProperties: true,
-    },
-    macros: {
-      type: 'array',
-      description: 'Placeholder/highlight macros (e.g. \\tofill{X}). Built-in macros are merged automatically; entries here add new macros or override built-ins by name.',
-      items: {
-        type: 'object',
-        properties: {
-          name: {
-            type: 'string',
-            description: 'Macro command name without leading backslash, e.g. "tofill" for \\tofill{...}',
-            pattern: '^[A-Za-z][A-Za-z0-9]*$',
-          },
-          default: {
-            type: 'object',
-            description: 'Default rendering rules across formats',
-            properties: {
-              color: { type: 'string', pattern: '^[0-9A-Fa-f]{6}$' },
-              bold: { type: 'boolean' },
-              italic: { type: 'boolean' },
-              bracket: { type: 'boolean', default: true },
-              prefix: { type: 'string' },
-              suffix: { type: 'string' },
-            },
-            additionalProperties: false,
-          },
-          formats: {
-            type: 'object',
-            description: 'Per-format overrides (keys: docx, pdf, latex, html, ...)',
-            additionalProperties: true,
-          },
-        },
-        required: ['name'],
-        additionalProperties: false,
-      },
-    },
-  },
-  additionalProperties: true,
-};
-
-/**
- * Validate a value against a simple schema
- */
-function validateValue(value: unknown, schema: Schema, path = ''): ValidationError[] {
-  const errors: ValidationError[] = [];
-
-  // Handle oneOf
-  if (schema.oneOf) {
-    const validForAny = schema.oneOf.some((subSchema) => {
-      const subErrors = validateValue(value, subSchema, path);
-      return subErrors.length === 0;
-    });
-    if (!validForAny) {
-      errors.push({
-        path,
-        message: `Value does not match any allowed type`,
-        value,
-      });
-    }
-    return errors;
-  }
-
-  // Type check
-  if (schema.type) {
-    const actualType = Array.isArray(value) ? 'array' : typeof value;
-    if (actualType !== schema.type) {
-      errors.push({
-        path,
-        message: `Expected ${schema.type}, got ${actualType}`,
-        value,
-      });
-      return errors; // Stop further validation if type is wrong
-    }
-  }
-
-  // String validation
-  if (schema.type === 'string' && typeof value === 'string') {
-    if (schema.pattern) {
-      const regex = new RegExp(schema.pattern);
-      if (!regex.test(value)) {
-        errors.push({
-          path,
-          message: `Value "${value}" does not match pattern ${schema.pattern}`,
-          value,
-        });
-      }
-    }
-    if (schema.enum && !schema.enum.includes(value)) {
-      errors.push({
-        path,
-        message: `Value "${value}" must be one of: ${schema.enum.join(', ')}`,
-        value,
-      });
-    }
-  }
-
-  // Number validation
-  if (schema.type === 'number' && typeof value === 'number') {
-    if (schema.minimum !== undefined && value < schema.minimum) {
-      errors.push({
-        path,
-        message: `Value ${value} is less than minimum ${schema.minimum}`,
-        value,
-      });
-    }
-    if (schema.maximum !== undefined && value > schema.maximum) {
-      errors.push({
-        path,
-        message: `Value ${value} is greater than maximum ${schema.maximum}`,
-        value,
-      });
-    }
-  }
-
-  // Array validation
-  if (schema.type === 'array' && Array.isArray(value)) {
-    if (schema.minItems !== undefined && value.length < schema.minItems) {
-      errors.push({
-        path,
-        message: `Array must have at least ${schema.minItems} items`,
-        value,
-      });
-    }
-    if (schema.maxItems !== undefined && value.length > schema.maxItems) {
-      errors.push({
-        path,
-        message: `Array must have at most ${schema.maxItems} items`,
-        value,
-      });
-    }
-    if (schema.items) {
-      value.forEach((item, index) => {
-        errors.push(...validateValue(item, schema.items!, `${path}[${index}]`));
-      });
-    }
-  }
-
-  // Object validation
-  if (schema.type === 'object' && typeof value === 'object' && value !== null) {
-    const obj = value as Record<string, unknown>;
-    if (schema.properties) {
-      for (const [key, propSchema] of Object.entries(schema.properties)) {
-        if (obj[key] !== undefined) {
-          errors.push(...validateValue(obj[key], propSchema, path ? `${path}.${key}` : key));
-        }
-      }
-    }
-    if (schema.required) {
-      for (const key of schema.required) {
-        if (obj[key] === undefined) {
-          errors.push({
-            path: path ? `${path}.${key}` : key,
-            message: `Required property "${key}" is missing`,
-            value: undefined,
-          });
-        }
-      }
-    }
-  }
-
-  return errors;
-}
-
-/**
- * Validate rev.yaml configuration
- */
-export function validateConfig(config: Record<string, unknown>): ValidationResult {
-  const errors = validateValue(config, revYamlSchema);
-  const warnings: ValidationWarning[] = [];
-
-  // Additional semantic validations
-  if (config.sections && Array.isArray(config.sections) && config.sections.length === 0) {
-    warnings.push({
-      path: 'sections',
-      message: 'No sections specified - build will auto-detect .md files',
-    });
-  }
-
-  if (config.bibliography && typeof config.bibliography === 'string' && !config.bibliography.endsWith('.bib')) {
-    warnings.push({
-      path: 'bibliography',
-      message: 'Bibliography file should have .bib extension',
-    });
-  }
-
-  const pdf = config.pdf as { linestretch?: number } | undefined;
-  if (pdf?.linestretch && (pdf.linestretch < 1 || pdf.linestretch > 3)) {
-    warnings.push({
-      path: 'pdf.linestretch',
-      message: 'Line stretch values outside 1-3 range may produce unexpected results',
-    });
-  }
-
-  // Check for common typos
-  const knownKeys = Object.keys(revYamlSchema.properties || {});
-  for (const key of Object.keys(config)) {
-    if (key.startsWith('_')) continue; // Internal keys
-    if (!knownKeys.includes(key)) {
-      // Check for similar keys (possible typos)
-      const similar = knownKeys.find(
-        (k) => levenshtein(key.toLowerCase(), k.toLowerCase()) <= 2
-      );
-      if (similar) {
-        warnings.push({
-          path: key,
-          message: `Unknown property "${key}" - did you mean "${similar}"?`,
-        });
-      }
-    }
-  }
-
-  return {
-    valid: errors.length === 0,
-    errors,
-    warnings,
-  };
-}
-
-/**
- * Format validation results for display
- */
-export function formatValidationResult(
-  result: ValidationResult,
-  chalk: { red: (s: string) => string; yellow: (s: string) => string; green: (s: string) => string }
-): string {
-  const lines: string[] = [];
-
-  if (result.errors.length > 0) {
-    lines.push(chalk.red('Configuration errors:'));
-    for (const error of result.errors) {
-      lines.push(chalk.red(`  ✗ ${error.path}: ${error.message}`));
-    }
-  }
-
-  if (result.warnings.length > 0) {
-    if (lines.length > 0) lines.push('');
-    lines.push(chalk.yellow('Warnings:'));
-    for (const warning of result.warnings) {
-      lines.push(chalk.yellow(`  ! ${warning.path}: ${warning.message}`));
-    }
-  }
-
-  if (result.valid && result.warnings.length === 0) {
-    lines.push(chalk.green('✓ Configuration is valid'));
-  }
-
-  return lines.join('\n');
-}
-
-/**
- * Levenshtein distance for typo detection
- */
-function levenshtein(a: string, b: string): number {
-  const matrix = Array(b.length + 1)
-    .fill(null)
-    .map(() => Array(a.length + 1).fill(null));
-  for (let i = 0; i <= a.length; i++) matrix[0][i] = i;
-  for (let j = 0; j <= b.length; j++) matrix[j][0] = j;
-  for (let j = 1; j <= b.length; j++) {
-    for (let i = 1; i <= a.length; i++) {
-      const cost = a[i - 1] === b[j - 1] ? 0 : 1;
-      matrix[j][i] = Math.min(
-        matrix[j][i - 1] + 1,
-        matrix[j - 1][i] + 1,
-        matrix[j - 1][i - 1] + cost
-      );
-    }
-  }
-  return matrix[b.length][a.length];
-}

package/lib/scientific-words.ts

@@ -1,73 +0,0 @@
-/**
- * Common scientific and academic words not in standard dictionaries
- * These words are accepted by Word's spellchecker
- */
-
-export const scientificWords = new Set([
-  // Biology/Ecology
-  'abiotic', 'biotic', 'biogeographic', 'biogeography', 'phenotypic', 'phenotype',
-  'anthropogenic', 'propagule', 'propagules', 'herbivory', 'herbivore', 'herbivores',
-  'ruderal', 'ruderals', 'refugia', 'refugium', 'hotspot', 'hotspots',
-  'biodiversity', 'ecosystem', 'ecosystems', 'ecotype', 'ecotypes',
-  'taxonomic', 'phylogenetic', 'phylogeny', 'morphological', 'morphology',
-  'allometric', 'allometry', 'biomass', 'biome', 'biomes',
-  'invasibility', 'invasive', 'invasives', 'neophyte', 'neophytes',
-  'archaeophyte', 'archaeophytes', 'naturalisation', 'naturalization',
-  'colonisation', 'colonization', 'dispersal', 'fecundity',
-  'phenology', 'phenological', 'ontogeny', 'ontogenetic',
-  'mesic', 'xeric', 'hydric', 'riparian', 'riverine',
-  'subalpine', 'alpine', 'boreal', 'temperate', 'tropical',
-  'heathland', 'heathlands', 'scrubland', 'scrublands', 'grassland', 'grasslands',
-  'broadleaf', 'broadleaved', 'coniferous', 'deciduous', 'evergreen',
-  'autochory', 'autochorous', 'zoochory', 'zoochorous',
-  'anemochory', 'anemochorous', 'hydrochory', 'hydrochorous',
-  'anthropochory', 'anthropochorous', 'hemerochor', 'hemerochorist',
-  'helophyte', 'helophytes', 'hydrophyte', 'hydrophytes',
-  'therophyte', 'therophytes', 'geophyte', 'geophytes',
-  'chamaephyte', 'chamaephytes', 'phanerophyte', 'phanerophytes',
-
-  // Statistics
-  'logit', 'logistic', 'probit', 'frequentist', 'bayesian',
-  'overdispersion', 'underdispersion', 'heteroscedasticity', 'homoscedasticity',
-  'multicollinearity', 'autocorrelation', 'covariate', 'covariates',
-  'parameterization', 'parameterisation', 'reparameterization',
-  'bootstrapping', 'resampling', 'imputation', 'interpolation',
-  'standardized', 'standardised', 'normalized', 'normalised',
-  'discretized', 'discretised', 'categorized', 'categorised',
-
-  // Compound words
-  'overrepresentation', 'underrepresentation', 'overrepresented', 'underrepresented',
-  'outcompete', 'outcompetes', 'outcompeted', 'outcompeting',
-  'subdataset', 'subgroup', 'subgroups', 'subtype', 'subtypes',
-  'dataset', 'datasets', 'datapoint', 'datapoints',
-  'spatiotemporal', 'spatio', 'geospatial',
-  'timestep', 'timesteps', 'timeframe', 'timeframes',
-  'warmup', 'backend', 'frontend', 'workflow', 'workflows',
-  'fallback', 'fallbacks', 'tradeoff', 'tradeoffs',
-
-  // Academic writing
-  'interpretability', 'reproducibility', 'replicability',
-  'hypothesise', 'hypothesised', 'hypothesize', 'hypothesized',
-  'analyse', 'analysed', 'analyze', 'analyzed',
-  'prioritise', 'prioritised', 'prioritize', 'prioritized',
-  'characterise', 'characterised', 'characterize', 'characterized',
-  'generalise', 'generalised', 'generalize', 'generalized',
-  'parameterise', 'parameterised', 'parameterize', 'parameterized',
-  'visualise', 'visualised', 'visualize', 'visualized',
-  'modelling', 'modeling', 'modelled', 'modeled',
-
-  // Geography
-  'unvegetated', 'landform', 'landforms', 'topographic', 'topography',
-  'elevational', 'latitudinal', 'longitudinal', 'altitudinal',
-
-  // Technical
-  'doi', 'dois', 'pdf', 'pdfs', 'csv', 'xlsx',
-  'pandoc', 'markdown', 'bibtex', 'crossref',
-
-  // R packages and tools
-  'brms', 'cmdstanr', 'rstanarm', 'lme', 'glmm', 'glmer', 'lmer',
-  'ggplot', 'dplyr', 'tidyr', 'tidyverse', 'rmarkdown',
-
-  // Common in papers
-  'foci', 'et', 'al', 'cf', 'eg', 'ie', 'vs',
-]);