forked from plotly/plotly_matlab
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathparseString.m
More file actions
257 lines (221 loc) · 10.7 KB
/
parseString.m
File metadata and controls
257 lines (221 loc) · 10.7 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
function formatStr = parseString(inputStr,interpreter)
% parseLatex(inputStr,d) converts TeX, and LaTeX
% strings into a format that preserves the text/math
% formatting structure used by mathjax for Plotly plots.
%
% TeX: parses through inputStr for instances of
% the specials characters: \, _, and ^. Uses whitespace
% as a delimter for the end of \reservedwords (enforced
% if not already present), uses either the enclosing { }
% brackets as delimeters for _ and ^ or simply the
% immediately proceeding character if no curly brackets
% are present. If the immediately proceeding character
% of ^ or _ is a \reservedword, the entire word up to the
% next whitespace is taken. All other characters are
% contained within \text{ } blocks. Resulting string is
% placed within inline: formatStr = $ ...parsedStr... $ delimeters.
%
% LaTeX: parses through inputStr for instances of $
% or $$. Assumes that $/$$ are only ever used as
% delimiters. Anything chars that do not fall within the
% $/$ or $$/$$ blocks are placed within a \text{ } block.
% Finally, all instances of $/$$ are removed and the
% resulting string is placed (if no $$ instance is present)
% within inline: formatStr = $ ...parsedStr...$ delimeters
% or (if an instance of $$ is present) wihtin block:
% formatStr $$... parsedStr ... $$ delimeters.
%initialize output
formatStr = inputStr;
if ~isempty(inputStr)
try
istex = false;
islatex = false;
%------- CONVERT CELL ARRAY TO STRING WITH LINE BREAKS -------%
if(iscell(inputStr))
if(size(inputStr,1)==1)
inputStr = strjoin(inputStr, '<br>');
else
inputStr = strjoin(inputStr', '<br>');
end
end
%------- PARSE TEX --------%
if(strcmp(interpreter,'tex'));
%add white space after reserved TeX words
formatStr = formatRW(inputStr);
%counter to iterate through formatStr
scount = 1;
%counter to iterate through formatStrCell
ccount = 1;
%iterate through formatStr
while scount <= (length(formatStr))
switch formatStr(scount)
%- \words - %
case '\'
istex = true;
formatStrCell{ccount} = [];
while(scount <= length(formatStr))
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
%break \word structure at whitespace: ' '
if(strcmp(formatStr(scount),' '))
scount = scount + 1;
break
end
scount = scount + 1;
end
ccount = ccount + 1;
%- _ subscripts -%
case '_'
istex = true;
formatStrCell{ccount} = [];
% look for enclosing { }
if(~strcmp(formatStr(scount+1),'{'))
% if no { } look for \ word
if(strcmp(formatStr(scount+1),'\'))
while (scount <= length(formatStr))
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
% break \word structure at whitespace: ' '
if(strcmp(formatStr(scount), ' '))
scount = scount + 1;
break
end
scount = scount + 1;
end
ccount = ccount + 1;
% if no { } and no \word
else
% take immediately proceeding char (existence assumed)
formatStrCell{ccount} = [formatStr(scount) formatStr(scount+1)];
scount = scount + 2;
ccount = ccount + 1;
end
else
% if enclosing { } are present
while (scount <= length(formatStr))
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
% break _{ structure at '}'
if(strcmp(formatStr(scount), '}'))
scount = scount + 1;
break
end
scount = scount + 1;
end
ccount = ccount + 1;
end
%- ^ superscripts - %
case '^'
istex = true;
formatStrCell{ccount} = [];
% look for enclosing { }
if(~strcmp(formatStr(scount+1),'{'))
% if no { } look for \ word
if(strcmp(formatStr(scount+1),'\'))
while ((scount <= length(formatStr)))
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
% break \word structure at whitespace: ' '
if(strcmp(formatStr(scount), ' '))
scount = scount + 1;
break
end
scount = scount + 1;
end
ccount = ccount + 1;
% if no { } and no \word
else
% take immediately proceeding char (existence assumed)
formatStrCell{ccount} = [formatStr(scount) formatStr(scount+1)];
scount = scount + 2;
ccount = ccount + 1;
end
else
% if enclosing { } are present
while ((scount <= length(formatStr)))
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
% break ^{ structure at '}'
if(strcmp(formatStr(scount), '}'))
scount = scount + 1;
break
end
scount = scount + 1;
end
ccount = ccount + 1;
end
%- \text{ } - %
otherwise
formatStrCell{ccount} = ['\text{'];
while (scount <= length(formatStr))
%break \text{ } structure at \word, _ or ^ chars
if(strcmp(formatStr(scount), '_') || strcmp(formatStr(scount), '^') || strcmp(formatStr(scount), '\') )
break
end
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
scount = scount + 1;
end
formatStrCell{ccount} = [formatStrCell{ccount} '}'];
ccount = ccount + 1;
end
end
%created parsedStr from formatStrCell
parsedStr = [ formatStrCell{:} ];
% place in inline: $...parsedStr...$ delimiters
if(istex)
formatStr = ['$' parsedStr '$'];
else
formatStr = inputStr;
end
%------- PARSE LATEX --------%
elseif(strcmp(interpreter,'latex'));
formatStr = inputStr;
%counter to iterate through formatStr
scount = 1;
%counter to iterate through formatStrCell
ccount = 1;
%look for existence of $$
dsPairs = regexp(formatStr,'\$\$');
%iterate through formatStr
while scount <= (length(formatStr))
if(strcmp(formatStr(scount),'$'))
islatex = true;
%- $$... $$ -%
if any(dsPairs == scount)
nextS = regexp(formatStr(scount+1:end),'\$\$','once');
formatStrCell{ccount} = formatStr(scount:scount + nextS);
scount = scount + nextS + 2;
ccount = ccount + 1;
%- $ ... $ -%
else
nextS = regexp(formatStr(scount+1:end),'\$','once');
formatStrCell{ccount} = formatStr(scount:scount + nextS);
scount = scount + nextS + 1;
ccount = ccount + 1;
end
%- \text{ } -%
else
formatStrCell{ccount} = ['\text{'];
while(scount<= length(formatStr))
if(strcmp(formatStr(scount),'$'))
break
end
formatStrCell{ccount} = [formatStrCell{ccount} formatStr(scount)];
scount = scount + 1;
end
formatStrCell{ccount} = [formatStrCell{ccount} '}'];
ccount = ccount + 1;
end
end
%remove all instances of $
parsedStr = [formatStrCell{:}];
parsedStr(regexp(parsedStr,'\$')) = '';
% place in inline: $...parsedStr...$
% or $$...parsedStr...$$ delimiters
if(islatex)
if(any(dsPairs))
formatStr = ['$$' parsedStr '$$'];
else
formatStr = ['$' parsedStr '$'];
end
else
formatStr = inputStr;
end
end
end
end