/*
** Copyright (c) 2007 D. Richard Hipp
**
** This program is free software; you can redistribute it and/or
** modify it under the terms of the Simplified BSD License (also
** known as the "2-Clause License" or "FreeBSD License".)
**
** This program is distributed in the hope that it will be useful,
** but without any warranty; without even the implied warranty of
** merchantability or fitness for a particular purpose.
**
** Author contact information:
**   drh@hwaci.com
**   http://www.hwaci.com/drh/

  *pMaxChars = COMMENT_LEGACY_LINE_LENGTH - indent;
  return -1;
#endif
}

/*
** This function checks the current line being printed against the original
** comment text.  Upon matching, it updates the provided character and line
** counts, if applicable.  The caller needs to emit a new line, if desired.
*/
static int comment_check_orig(
  const char *zOrigText, /* [in] Original comment text ONLY, may be NULL. */
  const char *zLine,     /* [in] The comment line to print. */
  int *pCharCnt,         /* [in/out] Pointer to the line character count. */
  int *pLineCnt          /* [in/out] Pointer to the total line count. */
){
  if( zOrigText && fossil_strcmp(zLine, zOrigText)==0 ){

    if( pCharCnt ) *pCharCnt = 0;
    if( pLineCnt ) (*pLineCnt)++;
    return 1;
  }
  return 0;
}

/*
** This function scans the specified comment line starting just after the
** initial index and returns the index of the next spacing character -OR-
** zero if such a character cannot be found.  For the purposes of this
** algorithm, the NUL character is treated the same as a spacing character.
*/
static int comment_next_space(
  const char *zLine, /* [in] The comment line being printed. */
  int index,         /* [in] The current character index being handled. */
  int *distUTF8      /* [out] Distance to next space in UTF-8 sequences. */
){
  int nextIndex = index + 1;
  int fNonASCII=0;
  for(;;){
    char c = zLine[nextIndex];
    if( (c&0x80)==0x80 ) fNonASCII=1;
    if( c==0 || fossil_isspace(c) ){
      if( distUTF8 ){
        if( fNonASCII!=0 ){
          *distUTF8 = strlen_utf8(&zLine[index], nextIndex-index);
        }else{
          *distUTF8 = nextIndex-index;
        }
      }
      return nextIndex;
    }
    nextIndex++;
  }
  return 0; /* NOT REACHED */
}

/*
** Count the number of UTF-8 sequences in a string. Incomplete, ill-formed and
** overlong sequences are counted as one sequence. The invalid lead bytes 0xC0
** to 0xC1 and 0xF5 to 0xF7 are allowed to initiate (ill-formed) 2- and 4-byte
** sequences, respectively, the other invalid lead bytes 0xF8 to 0xFF are
** treated as invalid 1-byte sequences (as lone trail bytes).
** Combining characters and East Asian Wide and Fullwidth characters are counted
** as one, so this function does not calculate the effective "display width".
*/
int strlen_utf8(const char *zString, int lengthBytes){
  int i;          /* Counted bytes. */
  int lengthUTF8; /* Counted UTF-8 sequences. */
#if 0
  assert( lengthBytes>=0 );
#endif
  for(i=0, lengthUTF8=0; i<lengthBytes; i++, lengthUTF8++){
    char c = zString[i];
    int cchUTF8=1; /* Code units consumed. */
    int maxUTF8=1; /* Expected sequence length. */
    if( (c&0xe0)==0xc0 )maxUTF8=2;          /* UTF-8 lead byte 110vvvvv */
    else if( (c&0xf0)==0xe0 )maxUTF8=3;     /* UTF-8 lead byte 1110vvvv */
    else if( (c&0xf8)==0xf0 )maxUTF8=4;     /* UTF-8 lead byte 11110vvv */
    while( cchUTF8<maxUTF8 &&
            i<lengthBytes-1 &&
            (zString[i+1]&0xc0)==0x80 ){    /* UTF-8 trail byte 10vvvvvv */
      cchUTF8++;
      i++;
    }
  }
  return lengthUTF8;
}

/*
** This function is called when printing a logical comment line to calculate
** the necessary indenting.  The caller needs to emit the indenting spaces.
*/
static void comment_calc_indent(
  const char *zLine, /* [in] The comment line being printed. */
  int indent,        /* [in] Number of spaces to indent, zero for none. */
  int trimCrLf,      /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,     /* [in] Non-zero to trim leading/trailing spaces. */
  int *piIndex       /* [in/out] Pointer to first non-space character. */
){



  if( zLine && piIndex ){
    int index = *piIndex;
    if( trimCrLf ){
      while( zLine[index]=='\r' || zLine[index]=='\n' ){ index++; }
    }
    if( trimSpace ){
      while( fossil_isspace(zLine[index]) ){ index++; }

  int trimCrLf,          /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,         /* [in] Non-zero to trim leading/trailing spaces. */
  int wordBreak,         /* [in] Non-zero to try breaking on word boundaries. */
  int origBreak,         /* [in] Non-zero to break before original comment. */
  int *pLineCnt,         /* [in/out] Pointer to the total line count. */
  const char **pzLine    /* [out] Pointer to the end of the logical line. */
){
  int index = 0, charCnt = 0, lineCnt = 0, maxChars, i;
  char zBuf[400]; int iBuf=0; /* Output buffer and counter. */
  int cchUTF8, maxUTF8;       /* Helper variables to count UTF-8 sequences. */
  if( !zLine ) return;
  if( lineChars<=0 ) return;
#if 0
  assert( indent<sizeof(zBuf)-5 );       /* See following comments to explain */
  assert( origIndent<sizeof(zBuf)-5 );   /* these limits. */
#endif
  if( indent>sizeof(zBuf)-6 ){
    /* Limit initial indent to fit output buffer. */
    indent = sizeof(zBuf)-6;
  }
  comment_calc_indent(zLine, indent, trimCrLf, trimSpace, &index);
  if( indent>0 ){
    for(i=0; i<indent; i++){
      zBuf[iBuf++] = ' ';
    }
  }
  if( origIndent>sizeof(zBuf)-6 ){
    /* Limit line indent to fit output buffer. */
    origIndent = sizeof(zBuf)-6;
  }
  maxChars = lineChars;
  for(;;){
    int useChars = 1;
    char c = zLine[index];
    /* Flush the output buffer if there's no space left for at least one more
    ** (potentially 4-byte) UTF-8 sequence, one level of indentation spaces,
    ** a new line, and a terminating NULL. */
    if( iBuf>sizeof(zBuf)-origIndent-6 ){
      zBuf[iBuf]=0;
      iBuf=0;
      fossil_print("%s", zBuf);
    }
    if( c==0 ){
      break;
    }else{
      if( origBreak && index>0 ){
        const char *zCurrent = &zLine[index];
        if( comment_check_orig(zOrigText, zCurrent, &charCnt, &lineCnt) ){
          zBuf[iBuf++] = '\n';
          comment_calc_indent(zLine, origIndent, trimCrLf, trimSpace, &index);
          for( i=0; i<origIndent; i++ ){
            zBuf[iBuf++] = ' ';
          }
          maxChars = lineChars;
        }
      }
      index++;
    }
    if( c=='\n' ){
      lineCnt++;
      charCnt = 0;
      useChars = 0;
    }else if( c=='\t' ){
      int distUTF8;
      int nextIndex = comment_next_space(zLine, index, &distUTF8);
      if( nextIndex<=0 || distUTF8>maxChars ){
        break;
      }
      charCnt++;
      useChars = COMMENT_TAB_WIDTH;
      if( maxChars<useChars ){
        zBuf[iBuf++] = ' ';
        break;
      }
    }else if( wordBreak && fossil_isspace(c) ){
      int distUTF8;
      int nextIndex = comment_next_space(zLine, index, &distUTF8);
      if( nextIndex<=0 || distUTF8>maxChars ){
        break;
      }
      charCnt++;
    }else{
      charCnt++;
    }
    assert( c!='\n' || charCnt==0 );
    zBuf[iBuf++] = c;
    /* Skip over UTF-8 sequences, see comment on strlen_utf8() for details. */
    cchUTF8=1; /* Code units consumed. */
    maxUTF8=1; /* Expected sequence length. */
    if( (c&0xe0)==0xc0 )maxUTF8=2;          /* UTF-8 lead byte 110vvvvv */
    else if( (c&0xf0)==0xe0 )maxUTF8=3;     /* UTF-8 lead byte 1110vvvv */
    else if( (c&0xf8)==0xf0 )maxUTF8=4;     /* UTF-8 lead byte 11110vvv */
    while( cchUTF8<maxUTF8 &&
            (zLine[index]&0xc0)==0x80 ){    /* UTF-8 trail byte 10vvvvvv */
      cchUTF8++;
      zBuf[iBuf++] = zLine[index++];
    }
    maxChars -= useChars;
    if( maxChars<=0 ) break;
    if( c=='\n' ) break;
  }
  if( charCnt>0 ){
    zBuf[iBuf++] = '\n';
    lineCnt++;
  }
  /* Flush the remaining output buffer. */
  if( iBuf>0 ){
    zBuf[iBuf]=0;
    iBuf=0;
    fossil_print("%s", zBuf);
  }
  if( pLineCnt ){
    *pLineCnt += lineCnt;
  }
  if( pzLine ){
    *pzLine = zLine + index;
  }

*/
static int comment_print_legacy(
  const char *zText, /* The comment text to be printed. */
  int indent,        /* Number of spaces to indent each non-initial line. */
  int width          /* Maximum number of characters per line. */
){
  int maxChars = width - indent;
  int si, sk, i, k, kc;
  int doIndent = 0;
  char *zBuf;
  char zBuffer[400];
  int lineCnt = 0;
  int cchUTF8, maxUTF8; /* Helper variables to count UTF-8 sequences. */

  if( width<0 ){
    comment_set_maxchars(indent, &maxChars);
  }
  if( zText==0 ) zText = "(NULL)";
  if( maxChars<=0 ){
    maxChars = strlen(zText);
  }
  /* Ensure the buffer can hold the longest-possible UTF-8 sequences. */
  if( maxChars >= (sizeof(zBuffer)/4-1) ){
    zBuf = fossil_malloc(maxChars*4+1);
  }else{
    zBuf = zBuffer;
  }
  for(;;){
    while( fossil_isspace(zText[0]) ){ zText++; }
    if( zText[0]==0 ){
      if( doIndent==0 ){
        fossil_print("\n");
        lineCnt = 1;
      }
      if( zBuf!=zBuffer) fossil_free(zBuf);
      return lineCnt;
    }
    for(sk=si=i=k=kc=0; zText[i] && kc<maxChars; i++){
      char c = zText[i];
      kc++; /* Count complete UTF-8 sequences. */
      /* Skip over UTF-8 sequences, see comment on strlen_utf8() for details. */
      cchUTF8=1; /* Code units consumed. */
      maxUTF8=1; /* Expected sequence length. */
      if( (c&0xe0)==0xc0 )maxUTF8=2;        /* UTF-8 lead byte 110vvvvv */
      else if( (c&0xf0)==0xe0 )maxUTF8=3;   /* UTF-8 lead byte 1110vvvv */
      else if( (c&0xf8)==0xf0 )maxUTF8=4;   /* UTF-8 lead byte 11110vvv */
      if( maxUTF8>1 ){
        zBuf[k++] = c;
        while( cchUTF8<maxUTF8 &&
                (zText[i+1]&0xc0)==0x80 ){  /* UTF-8 trail byte 10vvvvvv */
          cchUTF8++;
          zBuf[k++] = zText[++i];
        }
      }
      else if( fossil_isspace(c) ){
        si = i;
        sk = k;
        if( k==0 || zBuf[k-1]!=' ' ){
          zBuf[k++] = ' ';
        }
      }else{
        zBuf[k] = c;