ICU-22404 Work around rule file encoding issues.

eggrobin · Jul 13, 2023 · 9c6cc1c · 9c6cc1c
1 parent 84decc8
commit 9c6cc1c
Show file tree

Hide file tree

Showing 9 changed files with 9 additions and 9 deletions.
diff --git a/icu4c/source/data/brkitr/rules/line.txt b/icu4c/source/data/brkitr/rules/line.txt
@@ -361,7 +361,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_cj.txt b/icu4c/source/data/brkitr/rules/line_cj.txt
@@ -362,7 +362,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_loose.txt b/icu4c/source/data/brkitr/rules/line_loose.txt
@@ -372,7 +372,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_loose_cj.txt b/icu4c/source/data/brkitr/rules/line_loose_cj.txt
@@ -390,7 +390,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_loose_phrase_cj.txt b/icu4c/source/data/brkitr/rules/line_loose_phrase_cj.txt
@@ -403,7 +403,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_normal.txt b/icu4c/source/data/brkitr/rules/line_normal.txt
@@ -363,7 +363,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_normal_cj.txt b/icu4c/source/data/brkitr/rules/line_normal_cj.txt
@@ -369,7 +369,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_normal_phrase_cj.txt b/icu4c/source/data/brkitr/rules/line_normal_phrase_cj.txt
@@ -382,7 +382,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);

diff --git a/icu4c/source/data/brkitr/rules/line_phrase_cj.txt b/icu4c/source/data/brkitr/rules/line_phrase_cj.txt
@@ -374,7 +374,7 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 
 #LB 28a  Do not break Orthographic syllables
-($AP $CM*)? ($AS | $AK | [◌] ) ($CM* $VI $CM* ($AK | [◌] ))* ($CM* $VI | (($CM* ($AS | $AK | [◌] ) )? $CM* $VF))?;
+($AP $CM*)? ($AS | $AK | [\u25CC] ) ($CM* $VI $CM* ($AK | [\u25CC] ))* ($CM* $VI | (($CM* ($AS | $AK | [\u25CC] ) )? $CM* $VF))?;
 
 # LB 29
 $IS $CM* ($ALPlus | $HL);