The LICENSE has changed from a single license (Apache2) to a dual
license (Apache2 or MIT, at your option).
If you've previously used Wuffs under the Apache2 license, you are able
to keep doing so. No further action required by you.
The two files listed below (previous releases) are exceptions, as they
are older snapshots, frozen in time. Their license has not changed:
release/c/wuffs-v0.2.c
release/c/wuffs-v0.3.c
Every name in the AUTHORS file, other than Google Inc., has signed
Google's CLA (Contributor License Agreement).
Before this commit, line-comment token chains included the final "\n"
the way block-comments included the final "*/". The "\n" was mandatory.
However, when parsing with both QUIRK_ALLOW_COMMENT_LINE and
QUIRK_ALLOW_TRAILING_FILLER, input like "123//xyz" (without a "\n"
before the EOF) was rejected before and accepted after this commit.
So that line-comments are consistent, in that they either always or
never include the final "\n", they now never include the final "\n".
An input fragment (parsed with QUIRK_ALLOW_COMMENT_LINE) like
"//abc\n\t\t" was, before this commit, parsed as a 6 byte comment token
and a 2 byte other-filler token. That split is now 5+3.
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.687s
After:
real 0m1.677s
Ratio: 1.01x
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.765s
After:
real 0m1.687s
Ratio: 1.05x
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.799s
After:
real 0m1.765s
Ratio: 1.02x
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.911s
After:
real 0m1.799s
Ratio: 1.06x
Performance (on vanilla, comment-free JSON) slips a little.
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.863s
After:
real 0m1.911s
Ratio: 0.97x Inverse: 1.03x
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m1.949s
After:
real 0m1.863s
Ratio: 1.05x
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m3.612s
After:
real 0m1.949s
Ratio: 1.85x
Originally, the example/jsonptr program read JSON from stdin and wrote
JSON to stdout. Over the course of numerous recent commits, it gained
the ability to read either CBOR or JSON and write either CBOR or JSON.
(CBOR is, very roughly, a binary file format similar to the JSON text
file format). While a useful feature, the extra code hurt JSON-to-JSON
performance, the original motivating purpose of that program. This
commit reverts that feature, re-gaining original performance. (The
example/cbor-to-json and example/json-to-cbor programs were recently
added to convert between CBOR and JSON, covering that feature loss).
On a mid-range x86_64 laptop, processing the 181 MiB citylots.json file
from github.com/zemirco/sf-city-lots-json:
$ time gen/bin/example-jsonptr < citylots.json > /dev/null
Before this commit:
real 0m5.095s
After:
real 0m3.583s
Ratio: 1.42x
$ sloccount example/jsonptr/jsonptr.cc | grep ^cpp
Before this commit:
cpp: 1508 (100.00%)
After:
cpp: 869 (100.00%)
Ratio: 1.74x
This commit brings jsonptr.cc approximately to its state just before
168f60a7 "Add example/jsonptr -output-format=cbor flag" was committed,
although it keeps the flags added since then for allowing comments and
inf/NaN numbers.