def assert_parse(test, input_str, expect_tree): """ Run the parser to get the fst, then compare the result to the types in the ``expect_tree`` tuple tree. """ tokens = lex.tokenize(input_str) fst_root = parse.parse(tokens, test.parse_ctx) assert_parse_tree(test, [fst_root], expect_tree)
def parse_file(self, filepath): """Parse one file. Read the content, tokenize, and parse. """ if not os.path.exists(filepath): logger.warning("%s does not exist", filepath) return with io.open(filepath, "r", encoding="utf-8") as infile: infile_content = infile.read() tokens = lex.tokenize(infile_content) _ = parse.parse(tokens, self.get_db())
def assert_layout(test, input_str, expect_tree, strip_len=0): """ Run the formatter on the input string and assert that the result matches the output string """ input_str = strip_indent(input_str, strip_len) tokens = lex.tokenize(input_str) parse_tree = parse.parse(tokens, test.parse_db) box_tree = formatter.layout_tree(parse_tree, test.config) assert_layout_tree(test, [box_tree], expect_tree)
def do_layout_test(self, input_str, expect_tree, strip_len=6): """ Run the formatter on the input string and assert that the result matches the output string """ input_str = strip_indent(input_str, strip_len) tokens = lex.tokenize(input_str) parse_tree = parse.parse(tokens, self.parse_ctx) box_tree = formatter.layout_tree(parse_tree, self.config) assert_tree(self, [box_tree], expect_tree)
def process_file(config, infile_content): """ Parse the input cmake file, return the parse tree """ if config.format.line_ending == 'auto': detected = __main__.detect_line_endings(infile_content) config = config.clone() config.set_line_ending(detected) tokens = lex.tokenize(infile_content) parse_db = parse.funs.get_parse_db() parse_db.update(parse.funs.get_funtree(config.parse.fn_spec)) ctx = parse.ParseContext(parse_db, config=config) parse_tree = parse.parse(tokens, ctx) parse_tree.build_ancestry() return parse_tree
def process_file(config, infile_content, dump=None): """ Parse the input cmake file, re-format it, and print to the output file. """ outfile = io.StringIO(newline='') if config.format.line_ending == 'auto': detected = detect_line_endings(infile_content) config = config.clone() config.format.set_line_ending(detected) tokens = lex.tokenize(infile_content) if dump == "lex": for token in tokens: outfile.write("{}\n".format(token)) return outfile.getvalue(), True first_token = lex.get_first_non_whitespace_token(tokens) parse_db = parse.funs.get_parse_db() parse_db.update(parse.funs.get_funtree(config.parse.fn_spec)) if dump == "parsedb": dump_parsedb(parse_db, outfile) return outfile.getvalue(), True ctx = parse.ParseContext(parse_db, config=config) parse_tree = parse.parse(tokens, ctx) if dump == "parse": dump_parse([parse_tree], outfile) return outfile.getvalue(), True if dump == "markup": dump_markup([parse_tree], config, outfile) return outfile.getvalue(), True box_tree = formatter.layout_tree(parse_tree, config, first_token=first_token) if dump == "layout": formatter.dump_tree([box_tree], outfile) return outfile.getvalue(), True outstr = formatter.write_tree(box_tree, config, infile_content) if config.encode.emit_byteorder_mark: outstr = "\ufeff" + outstr outstr = formatter.replace_with_tabs(outstr, config) return (outstr, box_tree.reflow_valid)
def process_file(config, local_ctx, infile_content): """ Parse the input cmake file, re-format it, and print to the output file. """ if config.format.line_ending == 'auto': detected = __main__.detect_line_endings(infile_content) config = config.clone() config.set_line_ending(detected) checker = basic_checker.LintChecker(config, local_ctx) checker.check_basics(infile_content) tokens = lex.tokenize(infile_content) checker.check_tokens(tokens) parse_db = parse.funs.get_parse_db() parse_db.update(parse.funs.get_funtree(config.parse.fn_spec)) ctx = parse.ParseContext(parse_db, local_ctx, config) parse_tree = parse.parse(tokens, ctx) parse_tree.build_ancestry() checker.check_parse_tree(parse_tree)
def annotate_file(config, infile, outfile, outfmt=None): """ Parse the input cmake file, re-format it, and print to the output file. """ infile_content = infile.read() if config.format.line_ending == 'auto': detected = __main__.detect_line_endings(infile_content) config = config.clone() config.format.set_line_ending(detected) tokens = lex.tokenize(infile_content) parse_db = parse.funs.get_parse_db() parse_db.update(parse.funs.get_funtree(config.parse.fn_spec)) ctx = parse.ParseContext(parse_db) parse_tree = parse.parse(tokens, ctx) if outfmt == "page": html_content = render.get_html(parse_tree, fullpage=True) outfile.write(html_content) return if outfmt == "stub": html_content = render.get_html(parse_tree, fullpage=False) outfile.write(html_content) return if outfmt == "iframe": html_content = render.get_html(parse_tree, fullpage=True) wrap_lines = EMBED_TPL.split("\n") for line in wrap_lines[:2]: outfile.write(line) outfile.write("\n") outfile.write(html_content) for line in wrap_lines[3:]: outfile.write(line) outfile.write("\n") return raise ValueError("Invalid output format: {}".format(outfmt))
def inner_main(): """Parse arguments, open files, start work.""" logging.basicConfig(level=logging.INFO, format="%(levelname)s %(message)s") argparser = argparse.ArgumentParser( description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter, usage=USAGE_STRING) setup_argparse(argparser) args = argparser.parse_args() logging.getLogger().setLevel(getattr(logging, args.log_level.upper())) if args.outfile_path is None: args.outfile_path = '-' if '-' in args.infilepaths: assert len(args.infilepaths) == 1, \ "You cannot mix stdin as an input with other input files" if args.outfile_path == '-': outfile = io.open(os.dup(sys.stdout.fileno()), mode='w', encoding="utf-8", newline='') else: outfile = io.open(args.outfile_path, 'w', encoding="utf-8", newline='') returncode = 0 cfg = configuration.Configuration() collector = NameCollector() for infile_path in args.infilepaths: # NOTE(josh): have to load config once for every file, because we may pick # up a new config file location for each path if infile_path == '-': infile_path = os.dup(sys.stdin.fileno()) try: infile = io.open(infile_path, mode='r', encoding=cfg.encode.input_encoding, newline='') except (IOError, OSError): logger.error("Failed to open %s for read", infile_path) returncode = 1 continue try: with infile: infile_content = infile.read() except UnicodeDecodeError: logger.error("Unable to read %s as %s", infile_path, cfg.encode.input_encoding) returncode = 1 continue tokens = lex.tokenize(infile_content) parse_db = parse.funs.get_parse_db() ctx = parse.ParseContext(parse_db, config=cfg) parse_tree = parse.parse(tokens, ctx) parse_tree.build_ancestry() collector.collect_names(parse_tree) regexes = [ re.compile(pattern) for pattern in [ r"[A-Z][A-Z0-9_]+", # upper snake-case r"[a-z][a-z0-9_]+", # lower snake-case r"_[A-Z0-9_]+", # upper snake-case with underscore prefix r"_[a-z0-9_]+", # lower snake-case with underscore prefix ] ] outmap = {} patmap = {} for scope, varname in sorted(collector.varnames): if scope not in outmap: outmap[scope] = {} if scope not in patmap: patmap[scope] = {} for regex in regexes: patmap[scope][str(regex)] = 0 patmap[scope]["other"] = 0 for regex in regexes: if regex.match(varname): patmap[scope][str(regex)] += 1 break else: patmap[scope]["other"] += 1 if varname not in outmap[scope]: outmap[scope][varname] = 0 outmap[scope][varname] += 1 for scope, countmap in sorted(outmap.items()): outfile.write("\n{}\n{}\n".format(scope.name, "=" * len(scope.name))) for varname, count in sorted(countmap.items()): outfile.write("{}: {}\n".format(varname, count)) for scope, countmap in sorted(patmap.items()): outfile.write("\n{}\n{}\n".format(scope.name, "=" * len(scope.name))) for varname, count in sorted(countmap.items()): outfile.write("{}: {}\n".format(varname, count)) outfile.close() return returncode