diff --git a/html-preprocessor b/html-preprocessor index ae86aa8..34b24b7 100755 --- a/html-preprocessor +++ b/html-preprocessor @@ -227,6 +227,8 @@ def cmd_include(args: str, variables:dict[str, str]={}) -> str: while p.i < len(p): # at start of new line or end of comment p.next_line() ptrace(f"cmd_include: Processing at i={p.i} in line {pos2line(p.file, p.i)}") + # print(filename, p.i, pos2line(p.file, p.i)) + # TODO: hangs here if not p.find_comment_begin(): continue if not p.find_comment_end(): continue @@ -390,7 +392,7 @@ class HTMLParser(Parser): Parse a html file Each function operates the positon indicated by i until the position "line_end" """ - def __init__(self, file, variables:dict[str, str]): + def __init__(self, file, variables:dict[str, str], remove_comments=False): super().__init__(file) self.i = 0 self.variables = variables @@ -402,10 +404,11 @@ class HTMLParser(Parser): self.pos["conditional_block_beg"] = -1 # char pos of the first char of the last block, if waiting for elif, else or endif self.state["cmd_in_cmt"] = False self.state["last_condition"] = False # if the last if condition was true + self.remove_comments = remove_comments def next_line(self): """update i and line_end""" - self.pos["line_end"] = self.file.find('\n', self.i) + self.pos["line_end"] = self.file.find('\n', self.i+1) if self.pos["line_end"] < 0: self.pos["line_end"] = len(self) def use_variables(self): @@ -479,7 +482,7 @@ class HTMLParser(Parser): def command_end(self): if self.pos["cmd_end"] == self.pos["cmt_end"]: # reached end of comment - if self.state["cmd_in_cmt"]: + if self.state["cmd_in_cmt"] or self.remove_comments: # remove comment tags if a command was found remove_newline = 0 if self[self.pos["cmt_beg"]-1] == '\n' and self[self.pos["cmt_end"]+len(COMMENT_END)] == '\n': # if the comment consumes the whole line, remove the entire line @@ -502,8 +505,8 @@ class HTMLParser(Parser): # i = possible_command_end commented, because if something containing new commands is inserted we need to parse that as well -def parse_file(_file:str, variables:dict[str,str]): - p = HTMLParser(_file, variables) +def parse_file(_file:str, variables:dict[str,str], remove_comments): + p = HTMLParser(_file, variables, remove_comments=remove_comments) sidenav_include_pos = -1 while p.i < len(p): # at start of new line or end of comment @@ -570,6 +573,7 @@ def parse_file(_file:str, variables:dict[str,str]): else: cmd_output = "" p.replace_command_with_output(cmd_output) + p.command_end() if sidenav_include_pos >= 0: @@ -600,25 +604,17 @@ def substitute_variables(html:str, variables:dict[str, str]): """ ************************************************************ COMMAND LINE ************************************************************ """ -def missing_arg_val(arg): - print("Missing argument for", arg) - exit(1) - -def missing_arg(arg): - print("Missing ", arg) - exit(1) - - if __name__ == "__main__": parser = argparse.ArgumentParser(prog="bUwUma html preprocessor") parser.add_argument("--input", action="store", help="path to the input file", required=True) parser.add_argument("--output", action="store", help="output to this file", default="") parser.add_argument("--inplace", action="store_true", help="overwrite input file") - parser.add_argument("--var", action="append", help="set a variable --var varname=value") + parser.add_argument("--var", action="append", help="set a variable --var varname=value", default=[]) parser.add_argument("--output-deps", action="store", help="output a Makefile listing all dependencies", default="") parser.add_argument("--exit-on", action="store", help="exit when an error of the given severity occures", choices=["light", "serious", "critical"], default="serious") - parser.add_argument("--debug", action="store_true", help="be more verbose") - parser.add_argument("--trace", action="store_true", help="be extremly verbose") + parser.add_argument("--debug", action="store_true", help="be more verbose", default=False) + parser.add_argument("--trace", action="store_true", help="be extremly verbose", default=False) + parser.add_argument("--preserve-comments", action="store_true", help="do not remove normal html comments", default=False) variables:dict[str, str] = {} args = parser.parse_args() @@ -633,8 +629,9 @@ if __name__ == "__main__": args.input = args.input.strip(" ") args.output = args.output.strip(" ") args.output_deps = args.output_deps.strip(" ") - DEBUG = args.debug TRACE = args.trace + if args.trace: args.debug = True + DEBUG = args.debug # sanity checks if not path.isfile(args.input): @@ -656,8 +653,7 @@ if __name__ == "__main__": with open(args.input, "r") as file: target_html = file.read() - - output_html = parse_file(target_html, variables) + output_html = parse_file(target_html, variables, not args.preserve_comments) # pdebug(f"Output: {output_html}")