state-machine solve parsing of // in string

tools/unishox/compress-html-uncompressed.py

@@ -23,6 +23,31 @@ import unishox
 from os import listdir
 from os import path
 from datetime import datetime
+import re
+
+def extract_c_string(s: str) -> str:
+  state = 0
+  escape = False
+  out = ""
+  for c in s:
+    if state == 0:    # before string
+      if c == '"':      # entering string
+        out = '"'
+        state = 1
+      elif c == '/':    # start of comment before entering string
+        state = 99      # we're done
+    elif state == 1:  # in string
+      if escape:        # escaped char
+        out += '\\' + c
+        escape = False
+      elif c == '\\':   # escaped char
+        escape = True
+      elif c == '"':    # end of string
+        out += '"'
+        state = 99      # we're done
+      else:
+        out += c
+  return out
 
 path_compressed   = path.join('..','..','tasmota','html_compressed')
 path_uncompressed = path.join('..','..','tasmota','html_uncompressed')
@@ -56,10 +81,9 @@ for file in files:
           const_name = el[:-2] #extract the "const char" variable name
           line_list.pop(line_number)
     else: # remove line comments
-      line_el = line.rsplit("//")
-      # print('Splitted line list by //' % line_el)
-      # print(line_el[0])
-      text = text + line_el[0]
+      line_el = extract_c_string(line)
+      # print(line_el)
+      text = text + line_el
     line_number = line_number +1
 
   # print const_name