tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

improved word extraction a bit (unicode punctuation)

Browse Source
This commit is contained in:
dockes
2005-02-11 11:20:02 +00:00
parent 40a5905b15
commit d42db8b65d
6 changed files with 583 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/utils/Makefile
+1 -1
View File
@@ -35,7 +35,7 @@ trtranscode.o : ../utils/transcode.cpp
MIMEPARSE_OBJS= trmimeparse.o $(BIGLIB)
trmimeparse : $(MIMEPARSE_OBJS)
$(CXX) $(CXXFLAGS) -o mimeparse $(MIMEPARSE_OBJS) $(LIBICONV)
$(CXX) $(CXXFLAGS) -o trmimeparse $(MIMEPARSE_OBJS) $(LIBICONV)
trmimeparse.o : mimeparse.cpp
$(CXX) $(CXXFLAGS) -DTEST_MIMEPARSE -c -o trmimeparse.o \
mimeparse.cpp
src/utils/utf8iter.cpp
+40 -10
View File
@@ -1,10 +1,11 @@
#ifndef lint
static char rcsid[] = "@(#$Id: utf8iter.cpp,v 1.1 2005-02-10 19:52:50 dockes Exp $ (C) 2005 J.F.Dockes";
static char rcsid[] = "@(#$Id: utf8iter.cpp,v 1.2 2005-02-11 11:20:02 dockes Exp $ (C) 2005 J.F.Dockes";
#endif
#include <stdio.h>
#include <string>
#include <iostream>
#include <list>
#include <vector>
#include "debuglog.h"
using namespace std;
@@ -22,32 +23,61 @@ int main(int argc, char **argv)
const char *infile = argv[1];
const char *outfile = argv[2];
string in;
string out;
if (!file_to_string(infile, in)) {
cerr << "Cant read file\n" << endl;
exit(1);
}
vector<unsigned int>ucsout1;
string out, out1;
Utf8Iter it(in);
FILE *fp = fopen(outfile, "w");
if (fp == 0) {
fprintf(stderr, "cant create %s\n", outfile);
exit(1);
}
while (!it.eof()) {
int nchars = 0;
for (;!it.eof(); it++) {
unsigned int value = *it;
it.appendchartostring(out);
it++;
if (value == (unsigned int)-1) {
fprintf(stderr, "Conversion error occurred\n");
exit(1);
}
ucsout1.push_back(value);
fwrite(&value, 4, 1, fp);
if (!it.appendchartostring(out))
break;
out1 += it;
nchars++;
}
fclose(fp);
if (it.error()) {
fprintf(stderr, "Conversion error occurred\n");
exit(1);
}
fprintf(stderr, "nchars1 %d\n", nchars);
if (in != out) {
fprintf(stderr, "error: out != in\n");
exit(1);
}
if (in != out1) {
fprintf(stderr, "error: out1 != in\n");
exit(1);
}
vector<unsigned int>ucsout2;
it.rewind();
for (int i = 0; ; i++) {
unsigned int value;
if ((value = it[i]) == (unsigned int)-1) {
fprintf(stderr, "%d chars\n", i);
break;
}
it++;
ucsout2.push_back(value);
}
if (ucsout1 != ucsout2) {
fprintf(stderr, "error: ucsout1 != ucsout2\n");
exit(1);
}
fclose(fp);
exit(0);
}
src/utils/utf8iter.h
+103 -35
View File
@@ -1,6 +1,6 @@
#ifndef _UTF8ITER_H_INCLUDED_
#define _UTF8ITER_H_INCLUDED_
/* @(#$Id: utf8iter.h,v 1.1 2005-02-10 19:52:50 dockes Exp $ (C) 2004 J.F.Dockes */
/* @(#$Id: utf8iter.h,v 1.2 2005-02-11 11:20:02 dockes Exp $ (C) 2004 J.F.Dockes */
/**
* A small helper class to iterate over utf8 strings. This is not an
@@ -8,58 +8,113 @@
some specific uses
*/
class Utf8Iter {
unsigned int cl;
const string &s;
string::size_type pos;
bool bad;
int compute_cl() {
unsigned int cl; // Char length at current position if known
const string &s; // String we're working with
string::size_type pos; // Current position in string
bool bad; // Status
unsigned int m_charpos; // Current character posiiton
// Get character byte length at specified position
inline int get_cl(string::size_type p) const {
unsigned int z = (unsigned char)s[p];
if (z <= 127) {
return 1;
} else if (z>=192 && z <= 223) {
return 2;
} else if (z >= 224 && z <= 239) {
return 3;
} else if (z >= 240 && z <= 247) {
return 4;
} else if (z >= 248 && z <= 251) {
return 5;
} else if (z >= 252 && z <= 253) {
return 6;
}
return -1;
}
// Check position and cl against string length
bool poslok(string::size_type p, int l) const {
return p != string::npos && l > 0 && p + l <= s.length();
}
// Update current char length in object state. Assumes pos is inside string
inline int compute_cl() {
cl = 0;
if (bad)
return -1;
unsigned int z = (unsigned char)s[pos];
if (z <= 127) {
cl = 1;
} else if (z>=192 && z <= 223) {
cl = 2;
} else if (z >= 224 && z <= 239) {
cl = 3;
} else if (z >= 240 && z <= 247) {
cl = 4;
} else if (z >= 248 && z <= 251) {
cl = 5;
} else if (z >= 252 && z <= 253) {
cl = 6;
}
if (!cl || s.length() - pos < cl) {
cl = get_cl(pos);
if (!poslok(pos, cl)) {
bad = true;
cl = 0;
return -1;
}
return 0;
}
// Compute value at given position
inline unsigned int getvalueat(string::size_type p, int l) const {
switch (l) {
case 1: return (unsigned char)s[p];
case 2: return ((unsigned char)s[p] - 192) * 64 +
(unsigned char)s[p+1] - 128 ;
case 3: return ((unsigned char)s[p]-224)*4096 +
((unsigned char)s[p+1]-128)*64 +
(unsigned char)s[p+2]-128;
case 4: return ((unsigned char)s[p]-240)*262144 +
((unsigned char)s[p+1]-128)*4096 +
((unsigned char)s[p+2]-128)*64 +
(unsigned char)s[p+3]-128;
case 5: return ((unsigned char)s[p]-248)*16777216 +
((unsigned char)s[p+1]-128)*262144 +
((unsigned char)s[p+2]-128)*4096 +
((unsigned char)s[p+3]-128)*64 +
(unsigned char)s[p+4]-128;
case 6: return ((unsigned char)s[p]-252)*1073741824 +
((unsigned char)s[p+1]-128)*16777216 +
((unsigned char)s[p+2]-128)*262144 +
((unsigned char)s[p+3]-128)*4096 +
((unsigned char)s[p+4]-128)*64 +
(unsigned char)s[p+5]-128;
default:
return (unsigned int)-1;
}
}
public:
Utf8Iter(const string &in) : cl(0), s(in), pos(0), bad(false) {}
Utf8Iter(const string &in)
: cl(0), s(in), pos(0), bad(false), m_charpos(0) {}
void rewind() {
cl=0; pos=0; bad=false; m_charpos=0;
}
/** operator* returns the ucs4 value as a machine integer*/
unsigned int operator*() {
if (!cl && compute_cl() < 0)
return (unsigned int)-1;
switch (cl) {
case 1: return (unsigned char)s[pos];
case 2: return ((unsigned char)s[pos] - 192) * 64 + (unsigned char)s[pos+1] - 128 ;
case 3: return ((unsigned char)s[pos]-224)*4096 + ((unsigned char)s[pos+1]-128)*64 + (unsigned char)s[pos+2]-128;
case 4: return ((unsigned char)s[pos]-240)*262144 + ((unsigned char)s[pos+1]-128)*4096 +
((unsigned char)s[pos+2]-128)*64 + (unsigned char)s[pos+3]-128;
case 5: return ((unsigned char)s[pos]-248)*16777216 + ((unsigned char)s[pos+1]-128)*262144 +
((unsigned char)s[pos+2]-128)*4096 + ((unsigned char)s[pos+3]-128)*64 + (unsigned char)s[pos+4]-128;
case 6: return ((unsigned char)s[pos]-252)*1073741824 + ((unsigned char)s[pos+1]-128)*16777216 +
((unsigned char)s[pos+2]-128)*262144 + ((unsigned char)s[pos+3]-128)*4096 +
((unsigned char)s[pos+4]-128)*64 + (unsigned char)s[pos+5]-128;
default:
unsigned int val = getvalueat(pos, cl);
if (val == (unsigned int)-1) {
bad = true;
cl = 0;
return (unsigned int)-1;
}
return val;
}
/** "Direct" access. Awfully inefficient as we skip from start or current
* position at best. This can only be useful for a lookahead from the
* current position */
unsigned int operator[](unsigned int charpos) const {
string::size_type mypos = 0;
unsigned int mycp = 0;;
if (charpos >= m_charpos) {
mypos = pos;
mycp = m_charpos;
}
while (mypos < s.length() && mycp != charpos) {
mypos += get_cl(mypos);
++mycp;
}
if (mypos < s.length() && mycp == charpos) {
int l = get_cl(mypos);
if (poslok(mypos, l))
return getvalueat(mypos, get_cl(mypos));
}
return (unsigned int)-1;
}
string::size_type operator++(int) {
@@ -67,6 +122,7 @@ class Utf8Iter {
return string::npos;
}
pos += cl;
m_charpos++;
cl = 0;
return pos;
}
@@ -78,12 +134,24 @@ class Utf8Iter {
out += s.substr(pos, cl);
return true;
}
operator string() {
if (bad || (!cl && compute_cl() < 0)) {
return false;
}
return s.substr(pos, cl);
}
bool eof() {
return bad || pos == s.length();
}
bool error() {
return bad;
}
string::size_type getBpos() const {
return pos;
}
string::size_type getCpos() const {
return m_charpos;
}
};
src/utils/utf8testin.txt
+212
View File
@@ -0,0 +1,212 @@
UTF-8 encoded sample plain-text file
‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾
Markus Kuhn [ˈmaʳkʊs kuːn] <http://www.cl.cam.ac.uk/~mgk25/> — 2002-07-25
The ASCII compatible UTF-8 encoding used in this plain-text file
is defined in Unicode, ISO 10646-1, and RFC 2279.
Using Unicode/UTF-8, you can write in emails and source code things such as
Mathematics and sciences:
∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫
⎪⎢⎜│a²+b³ ⎟⎥⎪
∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪
⎪⎢⎜⎷ c₈ ⎟⎥⎪
ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬
⎪⎢⎜ ∞ ⎟⎥⎪
⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪
⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪
2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭
Linguistics and dictionaries:
ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn
Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ]
APL:
((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈
Nicer typography in plain text files:
╔══════════════════════════════════════════╗
║ ║
║ • ‘single’ and “double” quotes ║
║ ║
║ • Curly apostrophes: “We’ve been here” ║
║ ║
║ • Latin-1 apostrophe and accents: '´` ║
║ ║
║ • ‚deutsche‘ „Anführungszeichen“ ║
║ ║
║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║
║ ║
║ • ASCII safety test: 1lI|, 0OD, 8B ║
║ ╭─────────╮ ║
║ • the euro symbol: │ 14.95 € │ ║
║ ╰─────────╯ ║
╚══════════════════════════════════════════╝
Combining characters:
STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑
Greek (in Polytonic):
The Greek anthem:
Σὲ γνωρίζω ἀπὸ τὴν κόψη
τοῦ σπαθιοῦ τὴν τρομερή,
σὲ γνωρίζω ἀπὸ τὴν ὄψη
ποὺ μὲ βία μετράει τὴ γῆ.
᾿Απ᾿ τὰ κόκκαλα βγαλμένη
τῶν ῾Ελλήνων τὰ ἱερά
καὶ σὰν πρῶτα ἀνδρειωμένη
χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά!
From a speech of Demosthenes in the 4th century BC:
Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι,
ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς
λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ
τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿
εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ
πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν
οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι,
οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν
ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον
τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι
γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν
προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους
σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ
τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ
τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς
τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον.
Δημοσθένους, Γ´ ᾿Ολυνθιακὸς
Georgian:
From a Unicode conference invitation:
გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო
კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს,
ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს
ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი,
ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება
ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში,
ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში.
Russian:
From a Unicode conference invitation:
Зарегистрируйтесь сейчас на Десятую Международную Конференцию по
Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии.
Конференция соберет широкий круг экспертов по вопросам глобального
Интернета и Unicode, локализации и интернационализации, воплощению и
применению Unicode в различных операционных системах и программных
приложениях, шрифтах, верстке и многоязычных компьютерных системах.
Thai (UCS Level 2):
Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese
classic 'San Gua'):
[----------------------------|------------------------]
๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่
สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา
ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา
โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ
เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ
ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ
พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้
ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ
(The above is a two-column text. If combining characters are handled
correctly, the lines of the second column should be aligned with the
| character above.)
Ethiopian:
Proverbs in the Amharic language:
ሰማይ አይታረስ ንጉሥ አይከሰስ።
ብላ ካለኝ እንደአባቴ በቆመጠኝ።
ጌጥ ያለቤቱ ቁምጥና ነው።
ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው።
የአፍ ወለምታ በቅቤ አይታሽም።
አይጥ በበላ ዳዋ ተመታ።
ሲተረጉሙ ይደረግሙ።
ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል።
ድር ቢያብር አንበሳ ያስር።
ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም።
እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም።
የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ።
ሥራ ከመፍታት ልጄን ላፋታት።
ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል።
የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ።
ተንጋሎ ቢተፉ ተመልሶ ባፉ።
ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው።
እግርህን በፍራሽህ ልክ ዘርጋ።
Runes:
ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ
(Old English, which transcribed into Latin reads 'He cwaeth that he
bude thaem lande northweardum with tha Westsae.' and means 'He said
that he lived in the northern land near the Western Sea.')
Braille:
⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌
⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞
⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎
⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂
⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙
⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑
⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲
⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲
⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹
⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞
⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕
⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹
⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎
⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎
⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳
⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞
⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲
(The first couple of paragraphs of "A Christmas Carol" by Dickens)
Compact font selection example text:
ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789
abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ
–—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд
∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა
Greetings in various languages:
Hello world, Καλημέρα κόσμε, コンニチハ
Box drawing alignment tests: █
▉
╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳
║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳
║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳
╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳
║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎
║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏
╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█
▝▀▘▙▄▟