Skip to content

Commit b920d45

Browse files
eggrobineggrobin
committed
Merge remote-tracking branch 'la-vache/main' into L2/23-246 
2 parents e59bd66 + b753a41 commit b920d45

File tree

233 files changed

+500813
-408668
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

233 files changed

+500813
-408668
lines changed

‎.github/workflows/pipeline.yml‎

Lines changed: 87 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,87 @@
1+
name: Pipeline
2+
3+
4+
on:
5+
pull_request:
6+
branches: ['*']
7+
types: [opened, synchronize, reopened, labeled, unlabeled, ready_for_review, converted_to_draft, edited]
8+
9+
jobs:
10+
labels-for-repertoire-changes:
11+
name: Labels for repertoire changes
12+
outputs:
13+
repertoire-changed: ${{ steps.compare-repertoire.outputs.repertoire-changed }}
14+
pipeline-label: ${{ steps.check-labels.outputs.pipeline-label }}
15+
runs-on: ubuntu-latest
16+
steps:
17+
- name: Checkout merged UnicodeData.txt
18+
uses: actions/checkout@v3
19+
with:
20+
path: merged
21+
sparse-checkout: unicodetools/data/ucd/dev/UnicodeData.txt
22+
- name: Checkout base UnicodeData.txt
23+
uses: actions/checkout@v3
24+
with:
25+
ref: ${{ github.event.pull_request.base.sha }}
26+
path: base
27+
sparse-checkout: unicodetools/data/ucd/dev/UnicodeData.txt
28+
- name: Compare repertoire
29+
id: compare-repertoire
30+
run: |
31+
# Look for changes affecting the first two fields of UnicodeData.txt (code point and name).
32+
sed 's/^\([^;]*;[^;]*\);.*$/\1/' merged/unicodetools/data/ucd/dev/UnicodeData.txt > merged-repertoire.txt
33+
sed 's/^\([^;]*;[^;]*\);.*$/\1/' base/unicodetools/data/ucd/dev/UnicodeData.txt > base-repertoire.txt
34+
if diff base-repertoire.txt merged-repertoire.txt
35+
then echo "repertoire-changed=false" >> "$GITHUB_OUTPUT"
36+
else echo "repertoire-changed=true" >> "$GITHUB_OUTPUT"
37+
fi
38+
- name: Checkout Python scripts
39+
uses: actions/checkout@v3
40+
with:
41+
sparse-checkout: py/pipeline-workflow
42+
- name: Check pipeline labels
43+
id: check-labels
44+
if: steps.compare-repertoire.outputs.repertoire-changed == 'true'
45+
run: python3 py/pipeline-workflow/compare-repertoire.py
46+
l2-document:
47+
needs: labels-for-repertoire-changes
48+
if: ${{ always() && needs.labels-for-repertoire-changes.outputs.repertoire-changed == 'true' }}
49+
name: Proposal document
50+
runs-on: ubuntu-latest
51+
steps:
52+
- name: Checkout Python scripts
53+
uses: actions/checkout@v3
54+
with:
55+
sparse-checkout: py/pipeline-workflow
56+
- name: Check L2 document
57+
run: |
58+
python3 py/pipeline-workflow/check-l2-document.py
59+
utc-decision:
60+
needs: labels-for-repertoire-changes
61+
if: needs.labels-for-repertoire-changes.outputs.repertoire-changed == 'true' && needs.labels-for-repertoire-changes.outputs.pipeline-label != 'pipeline-recommended-to-UTC'
62+
name: UTC decision
63+
runs-on: ubuntu-latest
64+
steps:
65+
- name: Checkout Python scripts
66+
uses: actions/checkout@v3
67+
with:
68+
sparse-checkout: py/pipeline-workflow
69+
- name: Check UTC decision
70+
run: python3 py/pipeline-workflow/check-utc-decision.py
71+
draft-unless-approved:
72+
needs: labels-for-repertoire-changes
73+
if: needs.labels-for-repertoire-changes.outputs.repertoire-changed == 'true'
74+
name: Draft unless approved
75+
runs-on: ubuntu-latest
76+
steps:
77+
- name: Checkout Python scripts and DerivedAge.txt
78+
uses: actions/checkout@v3
79+
with:
80+
sparse-checkout: |
81+
py/pipeline-workflow
82+
unicodetools/data/ucd/dev/DerivedAge.txt
83+
- name: Check draft status
84+
env:
85+
PIPELINE_LABEL: ${{ needs.labels-for-repertoire-changes.outputs.pipeline-label }}
86+
run: python3 py/pipeline-workflow/check-draft-status.py
87+

‎UnicodeJsps/Dockerfile‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ FROM alpine as cbuild
33
WORKDIR /build
44
RUN apk add --update wget make gcc musl-dev
55
ARG CPATH=https://www.unicode.org/Public/PROGRAMS/BidiReferenceC/
6-
ARG CVERSION=15.0.0
6+
ARG CVERSION=15.1.0
77
RUN wget -np -nv --reject-regex='.*\.(lib|exe)$' --cut-dirs=4 -nH -r ${CPATH}${CVERSION}/
88
RUN cd source && gcc -I ../include/ -static -Os -o3 -o bidiref1 bidiref1.c brutils.c brtest.c brtable.c brrule.c
99
RUN ls -lh /build/source/bidiref1 && (/build/source/bidiref1 || true)

‎UnicodeJsps/src/main/java/org/unicode/jsp/ScriptTester.java‎

Lines changed: 27 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@
77
import com.ibm.icu.lang.UScript;
88
import com.ibm.icu.text.Normalizer;
99
import com.ibm.icu.text.UnicodeSet;
10+
import java.util.ArrayList;
1011
import java.util.BitSet;
1112
import java.util.Collection;
1213
import java.util.Comparator;
@@ -20,6 +21,7 @@
2021
import java.util.concurrent.atomic.AtomicInteger;
2122
import java.util.logging.Logger;
2223
import java.util.regex.Pattern;
24+
import org.unicode.props.UnicodeProperty;
2325

2426
/**
2527
* Class for testing whether strings have allowed combinations of multiple scripts.
@@ -319,6 +321,7 @@ public static class ScriptExtensions {
319321
public static final Comparator<BitSet> COMPARATOR =
320322
new Comparator<BitSet>() {
321323

324+
@Override
322325
public int compare(BitSet o1, BitSet o2) {
323326
int diff = o1.cardinality() - o2.cardinality();
324327
if (diff != 0) return diff;
@@ -344,6 +347,7 @@ private static class MyHandler extends FileUtilities.SemiFileReader {
344347

345348
UnicodeMap<BitSet> map = new UnicodeMap<BitSet>();
346349

350+
@Override
347351
public boolean handleLine(int start, int end, String[] items) {
348352
BitSet bitSet = new BitSet(LIMIT);
349353
for (String script : SPACES.split(items[1])) {
@@ -429,21 +433,39 @@ public static UnicodeMap<String> getScriptSpecialsNames() {
429433
return result;
430434
}
431435

432-
public static String[][] getScriptSpecialsAlternates() {
436+
public static String[][] getScriptSpecialsAlternates(UnicodeProperty scriptProp) {
433437
Collection<BitSet> availableValues = getScriptSpecials().getAvailableValues();
434-
String[][] result = new String[availableValues.size()][];
438+
List<String[]> result = new ArrayList<>();
435439
Set<String> names = new TreeSet<String>(); // to alphabetize
436440

437-
int i = 0;
438441
for (BitSet value : availableValues) {
439442
String baseName =
440443
ScriptExtensions.getNames(value, UProperty.NameChoice.LONG, ",", names);
441444
String altName =
442445
ScriptExtensions.getNames(value, UProperty.NameChoice.SHORT, ",", names);
443446
String[] row = {baseName, altName};
444-
result[i++] = row;
447+
result.add(row);
445448
}
446-
return result;
449+
450+
// Get the single values, and build alternate values for the property, for isValidValue
451+
// of a single script (eg Arab)
452+
List<String> values = scriptProp.getAvailableValues();
453+
for (String value : values) {
454+
List<String> row = new ArrayList<>();
455+
row.add(value);
456+
for (String alias : scriptProp.getValueAliases(value)) {
457+
if (!alias.equals(value)) {
458+
row.add(alias);
459+
}
460+
}
461+
// duplicate it whenever singular, because the tooling expects at least 2 values (ugg)
462+
if (row.size() == 1) {
463+
row.add(value);
464+
}
465+
result.add(row.toArray(new String[row.size()]));
466+
}
467+
468+
return result.toArray(new String[result.size()][]);
447469
}
448470

449471
private ScriptTester(UnicodeMap<BitSet> character_scripts) {

‎UnicodeJsps/src/main/java/org/unicode/jsp/UnicodeSetUtilities.java‎

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -150,6 +150,7 @@ public MySymbolTable() {
150150
// return null;
151151
// }
152152

153+
@Override
153154
public boolean applyPropertyAlias(
154155
String propertyName, String propertyValue, UnicodeSet result) {
155156
boolean status = false;
@@ -201,9 +202,11 @@ public boolean applyPropertyAlias(
201202
}
202203
;
203204
if (!status) {
204-
try {
205-
status = applyPropertyAlias0(prop, "No", result, !invert);
206-
} catch (Exception e) {
205+
if (prop.isType(UnicodeProperty.BINARY_OR_ENUMERATED_OR_CATALOG_MASK)) {
206+
try {
207+
status = applyPropertyAlias0(prop, "No", result, !invert);
208+
} catch (Exception e) {
209+
}
207210
}
208211
;
209212
if (!status) {
@@ -336,6 +339,7 @@ public ComparisonMatcher(String pattern, Relation comparator) {
336339
this.pattern = pattern;
337340
}
338341

342+
@Override
339343
public boolean test(String value) {
340344
int comp = comparator.compare(pattern, value.toString());
341345
switch (relation) {
@@ -352,6 +356,7 @@ public boolean test(String value) {
352356
}
353357
}
354358

359+
@Override
355360
public PatternMatcher set(String pattern) {
356361
this.pattern = pattern;
357362
return this;

0 commit comments

Comments
 (0)