Skip to content

improve parse_dom_table merge cell logic performance #1632

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

improve parse_dom_table merge cell logic performance #1632

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
eafc079
improve parse_dom_table merge cell logic performance
ThomasChan Sep 19, 2019
760c55d
improve parse_dom_table merge cell logic performance
ThomasChan Sep 19, 2019
aaefb53
fix xlsx merge cells logic
ThomasChan Sep 25, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 26 additions & 13 deletions xlsx.flow.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19160,29 +19160,42 @@ function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
var rows/*:HTMLCollection<HTMLTableRowElement>*/ = table.getElementsByTagName('tr');
var sheetRows = opts.sheetRows || 10000000;
var range/*:Range*/ = {s:{r:0,c:0},e:{r:0,c:0}};
var merges/*:Array<Range>*/ = [], midx = 0;
var merges/*:Array<Range>*/ = [], midx = 0, m, cInRange/*:Array<Range>*/ = [], cache/*:Object<Cache>*/ = {};
var rowinfo/*:Array<RowInfo>*/ = [];
var _R = 0, R = 0, _C, C, RS, CS;
var _R = 0, R = 0, _C, C, RS, CS, row, elts, elt, h, v, o, _t;
for(; _R < rows.length && R < sheetRows; ++_R) {
var row/*:HTMLTableRowElement*/ = rows[_R];
row/*:HTMLTableRowElement*/ = rows[_R];
if (is_dom_element_hidden(row)) {
if (opts.display) continue;
rowinfo[R] = {hidden: true};
}
var elts/*:HTMLCollection<HTMLTableCellElement>*/ = (row.children/*:any*/);
elts/*:HTMLCollection<HTMLTableCellElement>*/ = (row.children/*:any*/);
for(_C = C = 0; _C < elts.length; ++_C) {
var elt/*:HTMLTableCellElement*/ = elts[_C];
elt/*:HTMLTableCellElement*/ = elts[_C];
if (opts.display && is_dom_element_hidden(elt)) continue;
var v/*:string*/ = htmldecode(elt.innerHTML);
for(midx = 0; midx < merges.length; ++midx) {
var m/*:Range*/ = merges[midx];
if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
h/*:string*/ = elt.innerHTML;
v/*:string*/ = cache[h] || (cache[h] = htmldecode(elt.innerHTML));
cInRange.length = 0;
midx/*:number*/ = merges.length;
while (midx--) {
m/*:Range*/ = merges[midx];
if(m.s.r <= R && R <= m.e.r) {
cInRange.push(m.e.c);
}
}
if (cInRange.indexOf(C) !== -1) {
for (let i = 0; i < cInRange.length; i++) {
C += 1;
if (cInRange.indexOf(C) === -1) {
break;
}
}
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o/*:Cell*/ = {t:'s', v:v};
var _t/*:string*/ = elt.getAttribute("t") || "";
CS = +elt.colSpan || 1;
if((RS = +elt.rowSpan)>1 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
o/*:Cell*/ = {t:'s', v:v};
_t/*:string*/ = elt.getAttribute("t") || "";
if(v != null) {
if(v.length == 0) o.t = _t || 'z';
else if(opts.raw || v.trim().length == 0 || _t == "s"){}
Expand Down
39 changes: 26 additions & 13 deletions xlsx.js
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

39 changes: 26 additions & 13 deletions xlsx.mini.flow.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7379,29 +7379,42 @@ function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
var rows/*:HTMLCollection<HTMLTableRowElement>*/ = table.getElementsByTagName('tr');
var sheetRows = opts.sheetRows || 10000000;
var range/*:Range*/ = {s:{r:0,c:0},e:{r:0,c:0}};
var merges/*:Array<Range>*/ = [], midx = 0;
var merges/*:Array<Range>*/ = [], midx = 0, m, cInRange/*:Array<Range>*/ = [], cache/*:Object<Cache>*/ = {};
var rowinfo/*:Array<RowInfo>*/ = [];
var _R = 0, R = 0, _C, C, RS, CS;
var _R = 0, R = 0, _C, C, RS, CS, row, elts, elt, h, v, o, _t;
for(; _R < rows.length && R < sheetRows; ++_R) {
var row/*:HTMLTableRowElement*/ = rows[_R];
row/*:HTMLTableRowElement*/ = rows[_R];
if (is_dom_element_hidden(row)) {
if (opts.display) continue;
rowinfo[R] = {hidden: true};
}
var elts/*:HTMLCollection<HTMLTableCellElement>*/ = (row.children/*:any*/);
elts/*:HTMLCollection<HTMLTableCellElement>*/ = (row.children/*:any*/);
for(_C = C = 0; _C < elts.length; ++_C) {
var elt/*:HTMLTableCellElement*/ = elts[_C];
elt/*:HTMLTableCellElement*/ = elts[_C];
if (opts.display && is_dom_element_hidden(elt)) continue;
var v/*:string*/ = htmldecode(elt.innerHTML);
for(midx = 0; midx < merges.length; ++midx) {
var m/*:Range*/ = merges[midx];
if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
h/*:string*/ = elt.innerHTML;
v/*:string*/ = cache[h] || (cache[h] = htmldecode(elt.innerHTML));
cInRange.length = 0;
midx/*:number*/ = merges.length;
while (midx--) {
m/*:Range*/ = merges[midx];
if(m.s.r <= R && R <= m.e.r) {
cInRange.push(m.e.c);
}
}
if (cInRange.indexOf(C) !== -1) {
for (let i = 0; i < cInRange.length; i++) {
C += 1;
if (cInRange.indexOf(C) === -1) {
break;
}
}
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o/*:Cell*/ = {t:'s', v:v};
var _t/*:string*/ = elt.getAttribute("t") || "";
CS = +elt.colSpan || 1;
if((RS = +elt.rowSpan)>1 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
o/*:Cell*/ = {t:'s', v:v};
_t/*:string*/ = elt.getAttribute("t") || "";
if(v != null) {
if(v.length == 0) o.t = _t || 'z';
else if(opts.raw || v.trim().length == 0 || _t == "s"){}
Expand Down
39 changes: 26 additions & 13 deletions xlsx.mini.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7288,29 +7288,42 @@ function parse_dom_table(table, _opts) {
var rows = table.getElementsByTagName('tr');
var sheetRows = opts.sheetRows || 10000000;
var range = {s:{r:0,c:0},e:{r:0,c:0}};
var merges = [], midx = 0;
var merges = [], midx = 0, m, cInRange = [], cache = {};
var rowinfo = [];
var _R = 0, R = 0, _C, C, RS, CS;
var _R = 0, R = 0, _C, C, RS, CS, row, elts, elt, h, v, o, _t;
for(; _R < rows.length && R < sheetRows; ++_R) {
var row = rows[_R];
row = rows[_R];
if (is_dom_element_hidden(row)) {
if (opts.display) continue;
rowinfo[R] = {hidden: true};
}
var elts = (row.children);
elts = (row.children);
for(_C = C = 0; _C < elts.length; ++_C) {
var elt = elts[_C];
elt = elts[_C];
if (opts.display && is_dom_element_hidden(elt)) continue;
var v = htmldecode(elt.innerHTML);
for(midx = 0; midx < merges.length; ++midx) {
var m = merges[midx];
if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
h = elt.innerHTML;
v = h || (cache[h] = htmldecode(elt.innerHTML));
cInRange.length = 0;
midx = merges.length;
while (midx--) {
m = merges[midx];
if(m.s.r <= R && R <= m.e.r) {
cInRange.push(m.e.c);
}
}
if (cInRange.indexOf(C) !== -1) {
for (let i = 0; i < cInRange.length; i++) {
C += 1;
if (cInRange.indexOf(C) === -1) {
break;
}
}
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o = {t:'s', v:v};
var _t = elt.getAttribute("t") || "";
CS = +elt.colSpan || 1;
if((RS = +elt.rowSpan)>1 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
o = {t:'s', v:v};
_t = elt.getAttribute("t") || "";
if(v != null) {
if(v.length == 0) o.t = _t || 'z';
else if(opts.raw || v.trim().length == 0 || _t == "s"){}
Expand Down