Adding shrinking flag for cover and fastcover (#1656)

* Changed ERROR(GENERIC) excluding inits

* editing git ignore

* Edited init functions to size_t returns

* moved declarations earlier

* resolved issues with changes to init functions

* fixed style and an error check

* attempting to add tests that might trigger changes

* added && die to cases expecting to fail

* resolved no die on expected failed command

* fixed accel to be incorrect value

* Adding an automated shrinking option

* Fixing build

* finalizing fixes

* fix?

* Removing added comment in cover.h

* Styling fixes

* Merging with fb dev

* removing megic number for default regression

* Requested revisions

* fixing support for fast cover

* fixing casting errors

* parenthesis fix

* fixing some build nits

* resolving travis ci syntax

* might resolve all compilation issues

* removed unused variable

* remodeling the selectDict function

* fixing bad memory access

* fixing error checks

* fixed erroring check in selectDict

* fixing mixed declarations

* modify mixed declaration

* fixing nits and adding test cases

* Adding requested changes + fixed bug for error checking

* switched double comparison from != to <

* fixed declaration typing

* refactoring COVER_best_finish() and changing shrinkDict

* removing the const's

* modifying ZDICT_optimizeTrainFromBuffer_cover functions

* fixing potential bad memcpy

* fixing the error function for dict size
This commit is contained in:
Tyler-Tran
2019-06-27 16:26:57 -07:00
committed by Nick Terrell
parent 9038579ab2
commit c55d2e7ba3
7 changed files with 259 additions and 42 deletions
+8
View File
@@ -499,6 +499,10 @@ $ZSTD --train-fastcover=k=56,d=8 && die "Create dictionary without input file"
println "- Create dictionary with short dictID"
$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
println "- Create dictionaries with shrink-dict flag enabled"
$ZSTD --train-fastcover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict
$ZSTD --train-fastcover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict1
$ZSTD --train-fastcover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict2
println "- Create dictionary with size limit"
$ZSTD --train-fastcover=steps=8 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K
println "- Compare size of dictionary from 90% training samples with 80% training samples"
@@ -989,6 +993,10 @@ $ZSTD --train-cover=k=56,d=8 && die "Create dictionary without input file (shoul
println "- Create second (different) dictionary"
$ZSTD --train-cover=k=56,d=8 "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
$ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
println "- Create dictionary using shrink-dict flag"
$ZSTD --train-cover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict
$ZSTD --train-cover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict1
$ZSTD --train-cover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict2
println "- Create dictionary with short dictID"
$ZSTD --train-cover=k=46,d=8,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"