Moodle hack to make the excel generation lib really better

under UTF-8. Credit goes to Thomas Robb. MDL-9911
This commit is contained in:
stronk7
2007-07-28 00:00:45 +00:00
parent 4fb30fc90b
commit bb9950d1cc
+109 -21
View File
@@ -1294,7 +1294,7 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
$this->_append($header . $data);
}
/**
/**
* Calculate
* Handling of the SST continue blocks is complicated by the need to include an
* additional continuation byte depending on whether the string is split between
@@ -1302,6 +1302,18 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
* additional complications that will arise later when/if Rich Strings are
* supported).
*
* MOODLE NOTE!!
*
* The functions below
* _calculateSharedStringsSizes()
* _storeSharedStringsTable()
* have been inserted, replacing the original functions in order to make the function
* work with 2-byte data. The patch is discussed at this URL:
* http://pear.php.net/bugs/bug.php?id=1572
* and documented for Moodle at:
* http://tracker.moodle.org/browse/MDL-9911
* --Tom Robb, [email protected] July 23, 2007
*
* @access private
*/
function _calculateSharedStringsSizes()
@@ -1311,9 +1323,10 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
8228 : Maximum Excel97 block size
-4 : Length of block header
-8 : Length of additional SST header information
= 8216
-8 : Arbitrary number to keep within _add_continue() limit
= 8208
*/
$continue_limit = 8216;
$continue_limit = 8208;
$block_length = 0;
$written = 0;
$this->_block_sizes = array();
@@ -1321,6 +1334,9 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
foreach (array_keys($this->_str_table) as $string) {
$string_length = strlen($string);
$headerinfo = unpack("vlength/Cencoding", $string);
$encoding = $headerinfo["encoding"];
$split_string = 0;
// Block length is the total length of the strings that will be
// written out in a single SST or CONTINUE block.
@@ -1347,16 +1363,39 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
boundaries. Therefore, in some cases we need to reduce the
amount of available
*/
$align = 0;
# Only applies to Unicode strings
if ($encoding == 1) {
# Min string + header size -1
$header_length = 4;
if ($space_remaining > $header_length) {
# String contains 3 byte header => split on odd boundary
if (!$split_string && $space_remaining % 2 != 1) {
$space_remaining--;
$align = 1;
}
# Split section without header => split on even boundary
else if ($split_string && $space_remaining % 2 == 1) {
$space_remaining--;
$align = 1;
}
$split_string = 1;
}
}
if ($space_remaining > $header_length) {
// Write as much as possible of the string in the current block
$written += $space_remaining;
// Reduce the current block length by the amount written
$block_length -= $continue_limit - $continue;
$block_length -= $continue_limit - $continue - $align;
// Store the max size for this block
$this->_block_sizes[] = $continue_limit;
$this->_block_sizes[] = $continue_limit - $align;
// If the current string was split then the next CONTINUE block
// should have the string continue flag (grbit) set unless the
@@ -1398,13 +1437,19 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
This length is required to set the offsets in the BOUNDSHEET records since
they must be written before the SST records
*/
$total_offset = array_sum($this->_block_sizes);
// SST information
$total_offset += 8;
if (!empty($this->_block_sizes)) {
$total_offset += (count($this->_block_sizes)) * 4; // add CONTINUE headers
$tmp_block_sizes = array();
$tmp_block_sizes = $this->_block_sizes;
$length = 12;
if (!empty($tmp_block_sizes)) {
$length += array_shift($tmp_block_sizes); # SST
}
return $total_offset;
while (!empty($tmp_block_sizes)) {
$length += 4 + array_shift($tmp_block_sizes); # CONTINUEs
}
return $length;
}
/**
@@ -1421,9 +1466,31 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
function _storeSharedStringsTable()
{
$record = 0x00fc; // Record identifier
$length = 0x0008; // Number of bytes to follow
$total = 0x0000;
// Iterate through the strings to calculate the CONTINUE block sizes
$continue_limit = 8208;
$block_length = 0;
$written = 0;
$continue = 0;
// sizes are upside down
$this->_block_sizes = array_reverse($this->_block_sizes);
$length = array_pop($this->_block_sizes) + 8; // First block size plus SST information
$tmp_block_sizes = $this->_block_sizes;
// $tmp_block_sizes = array_reverse($this->_block_sizes);
# The SST record is required even if it contains no strings. Thus we will
# always have a length
#
if (!empty($tmp_block_sizes)) {
$length = 8 + array_shift($tmp_block_sizes);
}
else {
# No strings
$length = 8;
}
// Write the SST block header information
$header = pack("vv", $record, $length);
@@ -1431,18 +1498,14 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
$this->_append($header . $data);
// Iterate through the strings to calculate the CONTINUE block sizes
$continue_limit = 8216;
$block_length = 0;
$written = 0;
$continue = 0;
/* TODO: not good for performance */
foreach (array_keys($this->_str_table) as $string) {
$string_length = strlen($string);
$encoding = 0; // assume there are no Unicode strings
$headerinfo = unpack("vlength/Cencoding", $string);
$encoding = $headerinfo["encoding"];
$split_string = 0;
// Block length is the total length of the strings that will be
@@ -1473,6 +1536,30 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
// Unicode data should only be split on char (2 byte) boundaries.
// Therefore, in some cases we need to reduce the amount of available
// space by 1 byte to ensure the correct alignment.
$align = 0;
// Only applies to Unicode strings
if ($encoding == 1) {
// Min string + header size -1
$header_length = 4;
if ($space_remaining > $header_length) {
// String contains 3 byte header => split on odd boundary
if (!$split_string && $space_remaining % 2 != 1) {
$space_remaining--;
$align = 1;
}
// Split section without header => split on even boundary
else if ($split_string && $space_remaining % 2 == 1) {
$space_remaining--;
$align = 1;
}
$split_string = 1;
}
}
if ($space_remaining > $header_length) {
// Write as much as possible of the string in the current block
@@ -1483,7 +1570,7 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
$string = substr($string, $space_remaining);
// Reduce the current block length by the amount written
$block_length -= $continue_limit - $continue;
$block_length -= $continue_limit - $continue - $align;
// If the current string was split then the next CONTINUE block
// should have the string continue flag (grbit) set unless the
@@ -1503,7 +1590,8 @@ class Spreadsheet_Excel_Writer_Workbook extends Spreadsheet_Excel_Writer_BIFFwri
// Write the CONTINUE block header
if (!empty($this->_block_sizes)) {
$record = 0x003C;
$length = array_pop($this->_block_sizes);
$length = array_shift($tmp_block_sizes);
$header = pack('vv', $record, $length);
if ($continue) {
$header .= pack('C', $encoding);