Created
June 17, 2020 23:58
-
-
Save ctkirkman/1fbd9e2ac417d40be8be831474dba921 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import binascii | |
import re | |
def rtf_to_text(rtf): | |
def clear_cmd(rtf_parsed): | |
if rtf_parsed.get("cmd") == "f" and rtf_parsed.get("lvl") == 1: | |
encoding = rtf_parsed.get("fonts").get(rtf_parsed.get("cmd") + rtf_parsed.get("arg"), {}).get("encoding", "1252") | |
rtf_parsed["encoding"] = encoding | |
elif rtf_parsed.get("cmd") == "ansicpg": | |
encoding = rtf_parsed.get("arg") | |
rtf_parsed["encoding"] = encoding | |
elif rtf_parsed.get("cmd") == "line": | |
rtf_parsed["string"] += "\n" | |
elif rtf_parsed.get("cmd") == "par": | |
rtf_parsed["string"] += "\n" | |
elif rtf_parsed.get("cmd") == "tab": | |
rtf_parsed["string"] += "\t" | |
elif rtf_parsed.get("cmd") == "cell": | |
rtf_parsed["string"] += "\t" | |
rtf_parsed["cmd"] = "" | |
rtf_parsed["arg"] = "" | |
return rtf_parsed | |
languages = { | |
"1078": "af", | |
"1025": "ar-sa", | |
"1027": "ca", | |
"932": "ja", | |
"936": "zh-cn", | |
"950": "zh-tw", | |
"1028": "zh-tw", | |
"2052": "zh-cn", | |
"1029": "cs", | |
"1030": "da", | |
"1043": "nl-nl", | |
"2067": "nl-be", | |
"2057": "en-gb", | |
"1033": "en-us", | |
"1035": "fi", | |
"1036": "fr-fr", | |
"2060": "fr-be", | |
"3084": "fr-ca", | |
"4108": "fr-ch", | |
"1031": "de-de", | |
"2055": "de-ch", | |
"1253": "el", | |
"1032": "el", | |
"1037": "he", | |
"1038": "hu", | |
"1057": "id", | |
"1040": "it-it", | |
"1041": "ja", | |
"1042": "ko", | |
"1044": "no-no", | |
"1045": "pl", | |
"2070": "pt-pt", | |
"1046": "pt-br", | |
"1048": "ro", | |
"1049": "ru", | |
"2074": "sr-sp", | |
"1050": "hr", | |
"1051": "sk", | |
"1034": "es-es", | |
"2058": "es-mx", | |
"1053": "sv-se", | |
"1054": "th", | |
"1055": "tr", | |
"1066": "vi" | |
} | |
charsets = { | |
"0": "1252", | |
"128": "932", | |
"129": "949", | |
"134": "936", | |
"136": "950", | |
"161": "1253", | |
"162": "1254", | |
"177": "1255", | |
"178": "1256", | |
"186": "1257", | |
"204": "1251", | |
"222": "874", | |
"238": "1250" | |
} | |
rtf_parsed = { | |
"lvl": 0, | |
"cmd": "", | |
"arg": "", | |
"mode": "", | |
"hex": "", | |
"string": "", | |
"parsed": "", | |
"buffer": "", | |
"last": "", | |
"fonts": {}, | |
"languages": {}, | |
"encoding": "1033" | |
} | |
for c in rtf: | |
rtf_parsed["buffer"] += c | |
rtf_parsed["parsed"] += c | |
if c == "{" and rtf_parsed.get("last") != "\\": | |
if rtf_parsed.get("mode") == "cmd": | |
rtf_parsed[rtf_parsed.get("lvl")] = rtf_parsed.get("cmd") | |
rtf_parsed["buffer"] = "" | |
rtf_parsed["lvl"] += 1 | |
rtf_parsed["mode"] = "" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif c == "}" and rtf_parsed.get("last") != "\\": | |
rtf_parsed["lvl"] -= 1 | |
if rtf_parsed.get(rtf_parsed.get("lvl"), "") == "fonttbl": | |
font_cmd = rtf_parsed["buffer"].split(" ", 1)[0].split("\\") | |
font_entry = font_cmd[1] | |
for fcmd in font_cmd[2:]: | |
if "fcharset" in fcmd: | |
rtf_parsed["fonts"][font_entry] = {"encoding": charsets.get(fcmd.replace("fcharset", ""), "1252")} | |
elif rtf_parsed.get(rtf_parsed.get("lvl"), "") == "fldinst": | |
rtf_parsed["string"] += "(" + rtf_parsed.get("buffer", "").strip("}") + ")" | |
elif rtf_parsed.get(rtf_parsed.get("lvl"), "") == "fldrslt": | |
txt_val = re.sub(r"\\[0-9A-Za-z]+", "", rtf_parsed.get("buffer", "").strip("}")) | |
rtf_parsed["string"] += "[" + txt_val.strip() + "]" | |
rtf_parsed["buffer"] = "" | |
rtf_parsed["mode"] = "" | |
if rtf_parsed.get(rtf_parsed.get("lvl") + 1) is not None: | |
rtf_parsed[rtf_parsed.get("lvl") + 1] = "" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif c == "\\" and rtf_parsed.get("last") != "\\": | |
rtf_parsed["mode"] = "cmd" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif rtf_parsed.get("mode") == "cmd": | |
if re.match(r"[a-zA-Z\-]", c): | |
rtf_parsed["cmd"] += c | |
elif re.match(r"[0-9]", c): | |
rtf_parsed["arg"] += c | |
elif re.match(r"'", c) and rtf_parsed.get("lvl") == 1: | |
rtf_parsed["mode"] = "hex" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif re.match(r" ", c): | |
rtf_parsed["mode"] = "" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif re.match(r"\n", c) and rtf_parsed.get("lvl") == 1: | |
rtf_parsed = clear_cmd(rtf_parsed) | |
rtf_parsed["mode"] = "" | |
elif re.match(r"\\", c): | |
if rtf_parsed.get("lvl") == 1: | |
rtf_parsed["string"] += "\\" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
rtf_parsed["mode"] = "" | |
elif re.match(r"\~", c): | |
rtf_parsed["string"] += " " | |
rtf_parsed = clear_cmd(rtf_parsed) | |
rtf_parsed["mode"] = "" | |
elif re.match(r"\{", c): | |
rtf_parsed["string"] += "{" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
rtf_parsed["mode"] = "" | |
elif re.match(r"\}", c): | |
rtf_parsed["string"] += "}" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
rtf_parsed["mode"] = "" | |
elif re.match(r"[a-zA-Z0-9\s]", c) is None and rtf_parsed.get("lvl") == 1: | |
rtf_parsed["mode"] = "" | |
rtf_parsed = clear_cmd(rtf_parsed) | |
elif rtf_parsed.get("mode") == "hex": | |
rtf_parsed["hex"] += c | |
if len(rtf_parsed.get("hex")) % 2 == 0: | |
rtf_parsed["mode"] = "" | |
try: | |
encoding = rtf_parsed.get("encoding") | |
lang = languages.get(encoding, "en-us") | |
enc_str = binascii.unhexlify(rtf_parsed.get("hex")).decode(encoding) | |
rtf_parsed["string"] += enc_str | |
rtf_parsed["languages"][lang] = rtf_parsed.get("languages", {}).get(lang, 0) + len(enc_str) | |
rtf_parsed["hex"] = "" | |
except Exception as ex: | |
pass | |
elif rtf_parsed.get("mode") == "" and rtf_parsed.get("lvl") == 1: | |
encoding = rtf_parsed.get("encoding") | |
lang = languages.get(encoding, "en-us") | |
rtf_parsed["languages"][lang] = rtf_parsed.get("languages", {}).get(lang, 0) + 1 | |
rtf_parsed["string"] += c | |
else: | |
pass | |
# print("???") | |
rtf_parsed["last"] = c | |
return { | |
"text": rtf_parsed.get("string").strip("\n").strip(" "), | |
"lang": rtf_parsed.get("languages") | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment