9307175333

Committed 30 May 2024 06:08PM UTC coverage: 70.644% (-3.5%) from 74.124%

Build # 9307175333

Build Type

push

github

Committed by

web-flow

Commit Message

Merge b18390e74 into 70ff5c335

Run Details

1910 of 2592 new or added lines in 108 files covered. (73.69%)

901 existing lines in 52 files now uncovered.

12203 of 17274 relevant lines covered (70.64%)

6112.16 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/languages/my.lua

local function charclass (u)
   if (u >= 0x1000 and u <= 0x102A) or u == 0x104E or u == 0x25CC or u == 0x2d then
      return "CI"
   end
   if u == 0x1039 then
      return "VI"
   end
   if u >= 0x103B and u <= 0x103E then
      return "ME"
   end
   if u == 0x1031 then
      return "EV"
   end
   if u == 0x102F or u == 0x1030 then
      return "LV"
   end
   if u == 0x102D or u == 0x102E or u == 0x1032 then
      return "UV"
   end
   if u == 0x102C or u == 0x102B then -- 0x102b added by SC because it was splitting visargas
      return "AV"
   end
   if u == 0x1036 then
      return "AN"
   end
   if u == 0x103A then
      return "KI"
   end
   if u == 0x1037 then
      return "LD"
   end
   if u == 0x1038 then
      return "VG"
   end
   if u >= 0x1040 and u <= 0x1049 then
      return "MD"
   end
   if u == 0x104A or u == 0x104B or u == 0x2c or u == 0x2e or u == 0x3a or u == 0x3b then
      return "SE"
   end
   if u == 0x104C or u == 0x104D or u == 0x104F then
      return "VS"
   end
   if u >= 0x1050 and u <= 0x1055 then
      return "PL"
   end
   if u >= 0x1056 and u <= 0x1059 then
      return "PV"
   end
   if u == 0x20 or (u >= 0x2000 and u <= 0x200b) then
      return "SP"
   end
   if u == 0x28 or u == 0x5b or u == 0x7b or u == 0xab or u == 0x2018 or u == 0x201C or u == 0x2039 then
      return "LQ"
   end
   if u == 0x29 or u == 0x5d or u == 0x7d or u == 0xbb or u == 0x2019 or u == 0x201d or u == 0x203a then
      return "RQ"
   end
   if u == 0x200c then
      return "NJ"
   end
   if u == 0x2060 or u == 0x200d then
      return "WJ"
   end
   return "OT"
end

-- "Syllable Based Dual Weight Algorithm for Line Breaking in Myanmar Unicode"
-- Keith Stribley, http://thanlwinsoft.github.io/www.thanlwinsoft.org/ThanLwinSoft/MyanmarUnicode/Parsing/my2weightLineBreakAlg1_1.pdf
local p2 = SILE.types.node.penalty({ penalty = -25 })
local p1 = SILE.types.node.penalty({ penalty = -50 })

local penaltyFor = function (ca, cb)
   if ca == "WJ" or ca == "LQ" then
      return
   end
   if cb == "RQ" or cb == "WJ" then
      return
   end
   if ca == "OT" then
      return p1
   end
   if ca == "RQ" then
      return p2
   end
   if cb == "LQ" then
      return p2
   end

   if cb == "CI" then
      if ca == "AN" or ca == "KI" or ca == "LD" or ca == "VG" or ca == "PL" or ca == "PV" or ca == "RQ" then
         return p2
      end
      if ca == "MD" or ca == "SE" or ca == "VS" or ca == "SP" then
         return p1
      end
      return
   end
   if ca == "MD" and not (cb == "VI" or cb == "MD") then
      return p1
   end
   if cb == "PL" then
      if ca == "VI" then
         return
      end
      if ca == "SE" or ca == "VB" then
         return p1
      end
      return p2
   end
end

SILE.tokenizers.my = function (string)
   return coroutine.wrap(function ()
      local lastclass = ""
      local collection = ""
      for uchar in string.gmatch(string, "([%z\1-\127\194-\244][\128-\191]*)") do
         local thiscp = SU.codepoint(uchar)
         local thisclass = charclass(thiscp)
         if thisclass == "SP" then
            coroutine.yield({ separator = uchar })
         else
            local pen = penaltyFor(lastclass, thisclass)
            if pen then
               coroutine.yield({ node = pen })
               coroutine.yield({ string = collection })
               collection = ""
            end
            collection = collection .. uchar
         end
         lastclass = thisclass
      end
      coroutine.yield({ string = collection })
   end)
end

1	local function charclass (u)
2	if (u >= 0x1000 and u <= 0x102A) or u == 0x104E or u == 0x25CC or u == 0x2d then	×
3	return "CI"	×
4	end
5	if u == 0x1039 then	×
6	return "VI"	×
7	end
8	if u >= 0x103B and u <= 0x103E then	×
9	return "ME"	×
10	end
11	if u == 0x1031 then	×
12	return "EV"	×
13	end
14	if u == 0x102F or u == 0x1030 then	×
15	return "LV"	×
16	end
17	if u == 0x102D or u == 0x102E or u == 0x1032 then	×
18	return "UV"	×
19	end
20	if u == 0x102C or u == 0x102B then -- 0x102b added by SC because it was splitting visargas	×
21	return "AV"	×
22	end
23	if u == 0x1036 then	×
24	return "AN"	×
25	end
26	if u == 0x103A then	×
27	return "KI"	×
28	end
29	if u == 0x1037 then	×
30	return "LD"	×
31	end
32	if u == 0x1038 then	×
33	return "VG"	×
34	end
35	if u >= 0x1040 and u <= 0x1049 then	×
36	return "MD"	×
37	end
38	if u == 0x104A or u == 0x104B or u == 0x2c or u == 0x2e or u == 0x3a or u == 0x3b then	×
39	return "SE"	×
40	end
41	if u == 0x104C or u == 0x104D or u == 0x104F then	×
42	return "VS"	×
43	end
44	if u >= 0x1050 and u <= 0x1055 then	×
45	return "PL"	×
46	end
47	if u >= 0x1056 and u <= 0x1059 then	×
48	return "PV"	×
49	end
50	if u == 0x20 or (u >= 0x2000 and u <= 0x200b) then	×
51	return "SP"	×
52	end
53	if u == 0x28 or u == 0x5b or u == 0x7b or u == 0xab or u == 0x2018 or u == 0x201C or u == 0x2039 then	×
54	return "LQ"	×
55	end
56	if u == 0x29 or u == 0x5d or u == 0x7d or u == 0xbb or u == 0x2019 or u == 0x201d or u == 0x203a then	×
57	return "RQ"	×
58	end
59	if u == 0x200c then	×
60	return "NJ"	×
61	end
62	if u == 0x2060 or u == 0x200d then	×
63	return "WJ"	×
64	end
65	return "OT"	×
66	end
67
68	-- "Syllable Based Dual Weight Algorithm for Line Breaking in Myanmar Unicode"
69	-- Keith Stribley, http://thanlwinsoft.github.io/www.thanlwinsoft.org/ThanLwinSoft/MyanmarUnicode/Parsing/my2weightLineBreakAlg1_1.pdf
NEW 70	local p2 = SILE.types.node.penalty({ penalty = -25 })	×
NEW 71	local p1 = SILE.types.node.penalty({ penalty = -50 })	×
72
73	local penaltyFor = function (ca, cb)
74	if ca == "WJ" or ca == "LQ" then	×
75	return	×
76	end
77	if cb == "RQ" or cb == "WJ" then	×
78	return	×
79	end
80	if ca == "OT" then	×
81	return p1	×
82	end
83	if ca == "RQ" then	×
84	return p2	×
85	end
86	if cb == "LQ" then	×
87	return p2	×
88	end
89
90	if cb == "CI" then	×
91	if ca == "AN" or ca == "KI" or ca == "LD" or ca == "VG" or ca == "PL" or ca == "PV" or ca == "RQ" then	×
92	return p2	×
93	end
94	if ca == "MD" or ca == "SE" or ca == "VS" or ca == "SP" then	×
95	return p1	×
96	end
97	return	×
98	end
99	if ca == "MD" and not (cb == "VI" or cb == "MD") then	×
100	return p1	×
101	end
102	if cb == "PL" then	×
103	if ca == "VI" then	×
104	return	×
105	end
106	if ca == "SE" or ca == "VB" then	×
107	return p1	×
108	end
109	return p2	×
110	end
111	end
112
113	SILE.tokenizers.my = function (string)	×
114	return coroutine.wrap(function ()	×
115	local lastclass = ""	×
116	local collection = ""	×
117	for uchar in string.gmatch(string, "([%z\1-\127\194-\244][\128-\191]*)") do	×
118	local thiscp = SU.codepoint(uchar)	×
119	local thisclass = charclass(thiscp)	×
120	if thisclass == "SP" then	×
121	coroutine.yield({ separator = uchar })	×
122	else
123	local pen = penaltyFor(lastclass, thisclass)	×
124	if pen then	×
125	coroutine.yield({ node = pen })	×
126	coroutine.yield({ string = collection })	×
127	collection = ""	×
128	end
129	collection = collection .. uchar	×
130	end
131	lastclass = thisclass	×
132	end
133	coroutine.yield({ string = collection })	×
134	end)
135	end

sile-typesetter / sile / 9307175333

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous