-
Notifications
You must be signed in to change notification settings - Fork 0
/
blogparsec
executable file
·172 lines (139 loc) · 6.89 KB
/
blogparsec
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
#!/bin/perl -W
# Convert paper in "Astronomy & Astrophysics" LaTeX format to something resembling Markdown
# Manual post-processing is still necessary but a lot easier
#
# Elmar Klausmeier, 29-Sep-2023
use strict;
my ($ignore,$sectionCnt,$subSectionCnt,$replaceAlgo,$replaceTable) = (1,0,0,0,0);
my (@sections) = ();
print <<'EOF';
---
date: "2023-08-03 14:00:00"
title: "A Parsec-Scale Galactic 3D Dust Map out to 1.25 kpc from the Sun"
description: "A 3D map of the spatial distribution of interstellar dust extinction out to a distance of 1.25 kpc from the Sun"
MathJax: true
categories: ["mathematics", "astronomy"]
tags: ["interstellar dust", "interstellar medium", "Milky Way", "Gaia", "Gaussian processes", "Bayesian inference"]
---
EOF
while (<>) {
$ignore = 0 if (/\\author\{Gordian~Edenhofer/);
next if ($ignore);
# In this particular case we replace the two algorithms with a corresponding screenshot
if (/^\\begin\{algorithm/) {
$replaceAlgo = 1;
next;
} elsif (/^\s+Pseudocode for ICR creating a GP/) {
s/^(\s+)//;
s/(\\left|right)\\/$1\\\\/g; # probably MathJax bug
$replaceAlgo = 0;
print "\n\n";
} elsif (/^\s+Pseudocode for our expansion point variational/) {
s/^(\s+)//;
$replaceAlgo = 0;
print "\n\n";
} elsif ($replaceAlgo == 1) { next; }
if (/^\\begin\{table/) {
$replaceTable = 1;
next;
} elsif (/^\\end\{table/) {
$replaceTable = 0;
print <<'EOF';
Parameters of the prior distributions.
The parameters $s$, $\mathrm{scl}$, and $\mathrm{off}$ fully determine $\rho$.
They are jointly chosen to a prior yield the kernel reconstructed in [Leike2020][].
Name | Distribution | Mean | Standard Deviation | Degrees of Freedom
-----|--------------|------|--------------------|--------------------
_s_ | Normal | 0.0 | Kernel from [Leike2020][] | 786,432 × 772
scl | Log-Normal | 1.0 | 0.5 | 1
off | Normal | $-6.91\left(\approx\ln10^{-3}\right)$ <br>prior median extinction <br>from [Leike2020][] | 1.0 | 1
| | | Shape Parameter | Scale Parameter
$n_\sigma$ | Inverse Gamma | 3.0 | 4.0 | #Stars = 53,880,655
EOF
next;
} elsif ($replaceTable == 1) { next; }
s/^\\(author|institute)\{/\n<p>\u$1s:<\/p>\n\n1. /;
s/\~/ /g;
# Authors, institutions, abstract, etc.
s/\(\\begin\{CJK\*.+?CJK\*\}\)//;
s/\\inst\{(.+?)\}/ \($1\)/g;
if (/^\s+\\and/) { print "1. "; next; }
s/^\{% (\w+) heading \(.+$/\n\n_\u$1._ /;
s/^\\abstract/## Abstract/;
s/^\\keywords\{/__Key words.__ /;
# Lines to drop, not relevant
next if (/(^\\maketitle|^%\s+|^%In general|^\\date|^\\begin\{figure|^\\end\{figure|\s+\\centering|\s+\\begin\{split\}|\s+\\end\{split\}|^\s*\\label|^\\end\{acknowledgements\}|^\\FloatBarrier|^\\bibliograph|^\\end\{algorithm\}|^\\begin\{appendix|^\\end\{appendix\}|^\\end\{document\})/);
s/\s+%\s+[^%].+$//; # Drop LaTeX comments
s/\\fnmsep.+$//; # drop e-mail
print "\$\$\n" if (/(\\begin\{equation\}|\\begin\{align\})/); # enclose with $$a #1
# images
s/\s+\\includegraphics.+res\/(\w+)\}/!\[Photo\]\(\*<\?=\$rbase\?>\*\/img\/parsec_res\/$1\.png)/;
s/\s+\\subcaptionbox\{(.+?)\}\{\%/\n__$1__\n/g;
# MathJax doesn't know \nicefrac
s/\\nicefrac\{(.+?)\}\{(.+?)\}/\{$1\}\/\{$2\}/g;
s/\\coloneqq/:=/g; # MathJax doesn't know \coloneqq + \argmin + \SI
s/\\argmin/\\mathop\{\\hbox\{arg min\}\}/g;
s/\\SI(|\[parse\-numbers=false\])\{(.+?)\}/$2/g;
s/\\SIrange\{(.+?)\}\{(.+?)\}\{(|\\)([^\\]+?)\}/$1 $4 to $2 $4/g;
s/\\nano\\meter/nm/g;
s/\{\\pc\}/pc/g;
s/\{\\kpc\}/kpc/g;
s/(kpc|pc)\$/\\\\,\\hbox\{$1\}\$/g;
s/\{\\cubic\\pc\}/\\\\,\\hbox\{pc\}^3/g;
s/i\.e\.\\ /i.e., /g;
# Special cases
s/``([A-Za-z])/"$1/g; # double backquotes in LaTeX have an entirely different meaning than in Markdown
# These are probably MathJax bugs, which we correct here
s/\$\\tilde\{Q\}_\{\\bar\{\\xi\}\}\$/\$\\tilde\{Q\}\\_\{\\bar\{\\xi\}\}\$/g;
s/\$\\mathcal\{D\}_/\$\\mathcal\{D\}\\_/g;
s/\$P\(d\|\\mathcal\{D\}_/\$P\(d\|\\mathcal\{D\}\\_/g;
s/\$\\mathrm\{sf\}_/\$\\mathrm\{sf\}\\_/g;
s/\\url\{(.+?)\}/$1/g; # Markdown automatically URL-ifies URLs, so we can dispense \url{}
# Thousands separator, see https://stackoverflow.com/questions/33442240/perl-printf-to-use-commas-as-thousands-separator
s/\\num\[group-separator=\{,\}\]\{(\d+)\}/scalar reverse(join(",",unpack("(A3)*", reverse int($1))))/eg;
# Code
s/\\lstinline\|(.+?)\|/`$1`/g;
s/\\texttt\{(.+?)\}/`$1`/g;
s/quality\\_flags\$<\$8/quality_flags<8/g; # special case
# Special cases for preventing code blocks because of indentation
s/ (The angular resolution)/$1/;
s/ (The stated highest r)/$1/;
# sections + subsections
if (/\\section\{(.+?)\}\s*$/) {
my $s = $1;
++$sectionCnt; $subSectionCnt = 0;
push @sections, "- [$sectionCnt. $s](#s$sectionCnt)";
$_ = "\n## $sectionCnt. $s<a id=s$sectionCnt></a>\n";
} elsif (/\\subsection\{(.+?)\}\s*$/) {
my $s = $1;
++$subSectionCnt;
push @sections, "\t- [$sectionCnt.$subSectionCnt $s](#s${sectionCnt}_$subSectionCnt)";
$_ = "\n### $sectionCnt.$subSectionCnt $s<a id=s${sectionCnt}_$subSectionCnt></a>\n";
}
if (/(\\footnotetext\{%|^\\begin\{acknowledgements\})/) { print "> "; next; }
# Citations
s!\\citep\{([,\w]+)\}!'(['.join('][], [',split(/,/,$1)).'][])'!eg; # cite-paranthesis without any prefix text
s!\\citep\[(.+?)\]\[\]\{(\w+)\}!'('.$1.' ['.join('][], [',split(/,/,$2)).'][])'!eg; # citep with prefix text
#s/\\citep(|\[.*?\]\[\])\{(\w+)\}/'('.(length($1)>4?substr($1,1,-3).' ':'').'['.join('], [',split(',',$2)).'][])'/eg;
# First approach, now obsolete through above eval()-approach
#s/\\citep\{(\w+)\}/([$1][])/g;
#s/\\citep\{(\w+),(\w+)\}/([$1][], [$2][])/g;
#s/\\citep\{(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][], [$6][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][], [$6][], [$7][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][], [$6][], [$7][], [$8][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][], [$6][], [$7][], [$8][], [$9][])/g;
#s/\\citep\{(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+),(\w+)\}/([$1][], [$2][], [$3][], [$4][], [$5][], [$6][], [$7][], [$8][], [$9][], [$10][])/g;
s!\\(citet|citeauthor)\{([,\w]+)\}!'['.join('][], [',split(/,/,$2)).'][]'!eg; # we handle citet+citeauthor the same
#s/\\citet\{(\w+)\}/[$1][]/g;
print;
print "\$\$\n" if (/(\\end\{equation\}|\\end\{align\})/); # enclose with $$ #2
}
print "## Literature<a id=Literature></a>\n";
for (@sections) {
print $_ . "\n";
}
++$sectionCnt;
print "- [$sectionCnt. Literature](#Literature)\n";