Created
December 9, 2013 00:31
-
-
Save ror3d/7865655 to your computer and use it in GitHub Desktop.
Sample code for Andreu's project. It should get the data inside the <text> tag of a simple xml file and separate it into words.
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
void readFile() | |
{ | |
ifstream file; | |
char c; | |
enum ReadState { | |
StartFile, EndFile, Tag, Text | |
}; | |
ReadState state = StartFile; | |
ReadState lastState = StartFile; | |
stringstream ss; | |
while(file) | |
{ | |
file >> c; | |
switch(state) | |
{ | |
case StartFile: | |
if(c=='<') | |
{ | |
ss.str(""); | |
state = Tag; | |
lastState = StartFile; | |
} | |
break; | |
case Tag: | |
if(c=='>') | |
{ | |
if(ss.str().INSENSITIVE_EQUAL("text")) // Implement INSENSITIVE_EQUAL | |
{ | |
state = Text; | |
} | |
else | |
{ | |
state = lastState; | |
} | |
} | |
break; | |
case Text: | |
readText(file); | |
state = EndFile; | |
break; | |
} | |
} | |
} | |
void readText(istream file) | |
{ | |
stringstream ss; | |
char c; | |
bool hasAt = false; | |
bool startsWithLT = false; | |
while(file) | |
{ | |
file >> c; | |
if(ss.str().length() == 0) | |
{ | |
startsWithLT = (c == '<'); | |
} | |
if(c==' ' || c=='\n' || c=='\r' || c=='\t') // Add punctuation too? | |
{ | |
if(startsWithLT && ss.str().INSENSITIVE_EQUAL("</text>")) | |
{ | |
return; | |
} | |
if(hasAt) | |
{ | |
// Check if it's an email | |
} | |
// Here we would save the word somewhere | |
useWord(ss.str()); | |
hasAt = false; | |
ss.str(""); | |
} | |
else | |
{ | |
hasAt = hasAt || (c == '@'); | |
ss << c; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment