@qvac/harness 0.7.3 → 0.8.5

package/dist-lib/lib/office/python.js

@@ -1,32 +0,0 @@
-import b4a from 'b4a';
-import fs from 'fs';
-import { runPython } from '../tools/exec/adapters/python/pyodide.js';
-import { planVendoredInstall, vendoredManifest, wheelsDir } from '../tools/exec/adapters/python/wheels.js';
-const MAX_OFFICE_BYTES = 20 * 1024 * 1024;
-export async function extractWithPython(bytes, fileName, { format, packages, source, signal }) {
-    if (bytes.byteLength > MAX_OFFICE_BYTES) {
-        throw new Error(`document is too large to extract: ${bytes.byteLength} bytes, limit ${MAX_OFFICE_BYTES}`);
-    }
-    const dir = wheelsDir();
-    const manifest = vendoredManifest(dir);
-    const install = planVendoredInstall(packages, { dir, manifest });
-    if (!manifest ||
-        !install ||
-        !['micropip', ...install.packages].every((name) => Object.keys(manifest.files).some((file) => file.replaceAll('_', '-').startsWith(`${name}-`) && fs.existsSync(`${dir}/${file}`)))) {
-        throw new Error(`bundled ${format} extraction packages are unavailable`);
-    }
-    const result = await runPython(source, {
-        packages,
-        inputs: [{ path: `input.${format.toLowerCase()}`, bytes }],
-        outputs: ['extracted.txt'],
-        signal
-    });
-    if (result.exitCode !== 0) {
-        throw new Error(`${fileName}: ${result.stderr.trim()}`);
-    }
-    const output = result.files?.get('extracted.txt');
-    if (!output) {
-        throw new Error(result.rejected?.[0]?.reason ?? `${format} extraction produced no text file`);
-    }
-    return b4a.toString(output, 'utf8');
-}

package/dist-lib/lib/office/xlsx.d.ts

@@ -1 +0,0 @@
-export declare const XLSX_EXTRACT: string;

package/dist-lib/lib/office/xlsx.js

@@ -1,26 +0,0 @@
-export const XLSX_EXTRACT = `from openpyxl import load_workbook
-from pathlib import Path
-
-formulas = load_workbook("input.xlsx", read_only=True, data_only=False, keep_links=False)
-values = load_workbook("input.xlsx", read_only=True, data_only=True, keep_links=False)
-try:
-    with Path("extracted.txt").open("w", encoding="utf-8") as output:
-        for sheet in formulas.worksheets:
-            heading = False
-            cached = values[sheet.title]
-            sheet.reset_dimensions()
-            cached.reset_dimensions()
-            for cells, results in zip(sheet.iter_rows(), cached.iter_rows()):
-                row = [result.value if cell.data_type == "f" and result.value is not None else cell.value
-                       for cell, result in zip(cells, results)]
-                if not any(value is not None and str(value).strip() for value in row):
-                    continue
-                if not heading:
-                    output.write("Sheet: " + sheet.title + "\\n")
-                    heading = True
-                output.write(" | ".join("" if value is None else str(value).replace("\\n", " ")
-                                        for value in row) + "\\n")
-finally:
-    formulas.close()
-    values.close()
-`;

package/dist-lib/lib/tools/exec/adapters/python/create-effect.d.ts

@@ -1,7 +0,0 @@
-interface SourceHalves {
-    code: string;
-    text: string;
-}
-export declare function splitPythonSource(source: string): SourceHalves | null;
-export declare function pythonCreateEffect(args: Record<string, unknown>): 'read' | 'write';
-export {};

package/dist-lib/lib/tools/exec/adapters/python/create-effect.js

@@ -1,318 +0,0 @@
-import { IMAGE_INPUT, OFFICE_READ, PDF_READ, isEscaped, parseInputs, parseOutputs, parsePackages, stripCommentsAndDocstrings, tripleQuoteAt, unwrapPythonSource } from './python-adapter.js';
-const ARTIFACT_OUTPUT = /\.(docx|xlsx|pptx|pdf)$/i;
-const CREATE_PACKAGES = new Map([
-    ['python-docx', '1.2.0'],
-    ['openpyxl', '3.1.5'],
-    ['python-pptx', '1.0.2'],
-    ['fpdf2', '2.8.8'],
-    ['pillow', null]
-]);
-const PACKAGE_SPEC = /^([A-Za-z0-9](?:[A-Za-z0-9._-]*[A-Za-z0-9])?)(?:==([0-9A-Za-z.]+))?$/;
-const IMPORT_ROOTS = new Set(['docx', 'openpyxl', 'pptx', 'fpdf', 'datetime']);
-const BUILDER_ROOTS = new Set(['docx', 'openpyxl', 'pptx', 'fpdf']);
-const IMPORT_FROM = /^\s*from\s+([A-Za-z]\w*(?:\.[A-Za-z]\w*)*)\s+import\s+[A-Za-z]\w*(?:\s+as\s+[A-Za-z]\w*)?(?:\s*,\s*[A-Za-z]\w*(?:\s+as\s+[A-Za-z]\w*)?)*\s*$/;
-const ALLOWED_BUILTINS = new Set([
-    'True',
-    'False',
-    'None',
-    'Ellipsis',
-    'NotImplemented',
-    'Exception',
-    'ValueError',
-    'KeyError',
-    'IndexError',
-    'TypeError',
-    'RuntimeError',
-    'abs',
-    'all',
-    'any',
-    'bool',
-    'dict',
-    'divmod',
-    'enumerate',
-    'filter',
-    'float',
-    'int',
-    'len',
-    'list',
-    'map',
-    'max',
-    'min',
-    'pow',
-    'print',
-    'range',
-    'reversed',
-    'round',
-    'set',
-    'sorted',
-    'str',
-    'sum',
-    'tuple',
-    'zip'
-]);
-const PYTHON_BUILTINS = new Set(`ArithmeticError AssertionError AttributeError BaseException BaseExceptionGroup
-   BlockingIOError BrokenPipeError BufferError BytesWarning ChildProcessError
-   ConnectionAbortedError ConnectionError ConnectionRefusedError ConnectionResetError
-   DeprecationWarning EOFError Ellipsis EncodingWarning EnvironmentError Exception
-   ExceptionGroup False FileExistsError FileNotFoundError FloatingPointError
-   FutureWarning GeneratorExit IOError ImportError ImportWarning IndentationError
-   IndexError InterruptedError IsADirectoryError KeyError KeyboardInterrupt
-   LookupError MemoryError ModuleNotFoundError NameError None NotADirectoryError
-   NotImplemented NotImplementedError OSError OverflowError PendingDeprecationWarning
-   PermissionError ProcessLookupError PythonFinalizationError RecursionError
-   ReferenceError ResourceWarning RuntimeError RuntimeWarning StopAsyncIteration
-   StopIteration SyntaxError SyntaxWarning SystemError SystemExit TabError
-   TimeoutError True TypeError UnboundLocalError UnicodeDecodeError
-   UnicodeEncodeError UnicodeError UnicodeTranslateError UnicodeWarning UserWarning
-   ValueError Warning ZeroDivisionError abs aiter all anext any ascii bin bool
-   breakpoint bytearray bytes callable chr classmethod compile complex copyright
-   credits delattr dict dir divmod enumerate eval exec execfile exit filter float
-   format frozenset getattr globals hasattr hash help hex id input int isinstance
-   issubclass iter len license list locals map max memoryview min next object oct
-   open ord pow print property quit range reload repr reversed round set setattr
-   slice sorted staticmethod str sum super tuple type unicode vars zip`.split(/\s+/));
-const DENIED_TOKENS = new Set([
-    'os',
-    'sys',
-    'js',
-    'pyodide',
-    'micropip',
-    'builtins',
-    'importlib',
-    'inspect',
-    'ctypes',
-    'subprocess',
-    'platform',
-    'shutil',
-    'pathlib',
-    'glob',
-    'tempfile',
-    'gc',
-    'socket',
-    'requests',
-    'urllib',
-    'http',
-    'ssl',
-    'ftplib',
-    'smtplib',
-    'webbrowser',
-    'pickle',
-    'marshal',
-    'base64',
-    'codecs',
-    'io',
-    'threading',
-    'asyncio',
-    'async',
-    'await',
-    'format_map',
-    'vformat'
-]);
-const INTROSPECTION_TOKEN = /^(?:gi|cr|ag|f|tb|im|func)_/;
-function isFStringPrefix(code) {
-    const prefix = /[A-Za-z]{1,3}$/.exec(code)?.[0] ?? '';
-    return prefix.length <= 2 && /f/i.test(prefix);
-}
-export function splitPythonSource(source) {
-    let code = '';
-    let text = '';
-    let i = 0;
-    while (i < source.length) {
-        const ch = source[i];
-        if (ch === '#') {
-            while (i < source.length && source[i] !== '\n') {
-                text += source[i];
-                i++;
-            }
-            continue;
-        }
-        const triple = tripleQuoteAt(source, i);
-        const quote = triple ?? (ch === '"' || ch === "'" ? ch : null);
-        if (quote) {
-            const fstring = isFStringPrefix(code);
-            const end = scanLiteral(source, i + quote.length, { quote, fstring });
-            if (!end) {
-                return null;
-            }
-            code += '""';
-            text += end.text;
-            code += end.code;
-            i = end.index;
-            continue;
-        }
-        code += ch;
-        i++;
-    }
-    return { code, text };
-}
-function scanLiteral(source, start, { quote, fstring }) {
-    let text = '';
-    let code = '';
-    let i = start;
-    while (i < source.length) {
-        if (source.startsWith(quote, i) && !isEscaped(source, i)) {
-            return { index: i + quote.length, text, code };
-        }
-        const ch = source[i];
-        if (fstring && (ch === '{' || ch === '}')) {
-            if (source[i + 1] === ch) {
-                text += ch + ch;
-                i += 2;
-                continue;
-            }
-            if (ch === '}') {
-                return null;
-            }
-            const interior = scanInterpolation(source, i + 1);
-            if (!interior) {
-                return null;
-            }
-            code += ` ${interior.code} `;
-            text += interior.text;
-            i = interior.index;
-            continue;
-        }
-        text += ch;
-        i++;
-    }
-    return null;
-}
-function scanInterpolation(source, start) {
-    let code = '';
-    let text = '';
-    let depth = 1;
-    let nested = null;
-    let i = start;
-    while (i < source.length) {
-        const ch = source[i];
-        if (nested) {
-            if (ch === nested && !isEscaped(source, i)) {
-                nested = null;
-            }
-            else {
-                text += ch;
-            }
-            i++;
-            continue;
-        }
-        if (ch === '"' || ch === "'") {
-            nested = ch;
-            i++;
-            continue;
-        }
-        if (ch === '{') {
-            depth++;
-        }
-        if (ch === '}') {
-            depth--;
-            if (depth === 0) {
-                return { index: i + 1, text, code };
-            }
-        }
-        code += ch;
-        i++;
-    }
-    return null;
-}
-function isKeywordArgument(code, start, length) {
-    const before = code.slice(0, start).trimEnd();
-    const last = before[before.length - 1];
-    if (last !== '(' && last !== ',') {
-        return false;
-    }
-    const after = code.slice(start + length).trimStart();
-    return after.startsWith('=') && after[1] !== '=';
-}
-function lintCreateSource(source) {
-    const halves = splitPythonSource(source);
-    if (!halves) {
-        return 'write';
-    }
-    if (halves.text.includes('__')) {
-        return 'write';
-    }
-    if (/\\(?:x[0-9A-Fa-f]|u[0-9A-Fa-f]|U[0-9A-Fa-f]|N\{|[0-7])/.test(halves.text)) {
-        return 'write';
-    }
-    if (/[^\x20-\x7e\t\r\n\f]/.test(halves.code)) {
-        return 'write';
-    }
-    let builder = false;
-    for (const line of halves.code.split('\n')) {
-        for (const statement of line.split(';')) {
-            if (!/\b(?:from|import)\b/.test(statement))
-                continue;
-            const match = IMPORT_FROM.exec(statement);
-            if (!match) {
-                return 'write';
-            }
-            const root = match[1].split('.')[0];
-            if (!IMPORT_ROOTS.has(root)) {
-                return 'write';
-            }
-            if (BUILDER_ROOTS.has(root)) {
-                builder = true;
-            }
-        }
-    }
-    if (!builder) {
-        return 'write';
-    }
-    for (const match of halves.code.matchAll(/[A-Za-z_]\w*/g)) {
-        const token = match[0];
-        if (token.includes('__') || DENIED_TOKENS.has(token) || INTROSPECTION_TOKEN.test(token)) {
-            return 'write';
-        }
-        if (isKeywordArgument(halves.code, match.index, token.length)) {
-            continue;
-        }
-        if (PYTHON_BUILTINS.has(token) && !ALLOWED_BUILTINS.has(token)) {
-            return 'write';
-        }
-    }
-    const openers = stripCommentsAndDocstrings(source);
-    const reads = [new RegExp(OFFICE_READ.source), new RegExp(PDF_READ.source)];
-    if (reads.some((pattern) => pattern.test(openers))) {
-        return 'write';
-    }
-    return 'read';
-}
-export function pythonCreateEffect(args) {
-    const outputs = parseOutputs(args.outputs);
-    if (!Array.isArray(outputs) || outputs.length === 0) {
-        return 'write';
-    }
-    if (!outputs.every((name) => ARTIFACT_OUTPUT.test(name))) {
-        return 'write';
-    }
-    const packages = parsePackages(args.packages);
-    if (packages && 'error' in packages) {
-        return 'write';
-    }
-    for (const spec of packages ?? []) {
-        const match = PACKAGE_SPEC.exec(spec);
-        if (!match) {
-            return 'write';
-        }
-        const name = match[1].toLowerCase().replace(/[_.]+/g, '-');
-        if (!CREATE_PACKAGES.has(name)) {
-            return 'write';
-        }
-        if (CREATE_PACKAGES.get(name) !== (match[2] ?? null)) {
-            return 'write';
-        }
-    }
-    const inputs = parseInputs(args.inputs);
-    if (inputs && 'error' in inputs) {
-        return 'write';
-    }
-    if ((inputs ?? []).some((input) => !IMAGE_INPUT.test(input.path))) {
-        return 'write';
-    }
-    const command = String(args.command ?? '');
-    const source = unwrapPythonSource(command) ?? command;
-    if (!source.trim()) {
-        return 'write';
-    }
-    return lintCreateSource(source);
-}