From ebff8fb7f1dbf265937eb078626187069433cca7 Mon Sep 17 00:00:00 2001
From: Stephan Porada <sporada@uni-bielefeld.de>
Date: Mon, 14 Oct 2019 14:00:41 +0200
Subject: [PATCH] Add author and title tags. Fix some errors in note.txt

---
 docs/note.txt     |  5 ++++-
 files/utopien.vrt | 48 +++++++++++++++++++++++------------------------
 2 files changed, 28 insertions(+), 25 deletions(-)

diff --git a/docs/note.txt b/docs/note.txt
index 8f2ea3f..163bb05 100644
--- a/docs/note.txt
+++ b/docs/note.txt
@@ -1,7 +1,9 @@
 # Enter bash in cqpwebserver
-docker exec -it cqperver_cqpserver_1 /bin/bash
+docker exec -it cqpserver_cqpserver_1 /bin/bash
 
 ## Encode example corpus
+mkdir /corpora/data/example
+
 cwb-encode -d /corpora/data/example \
            -f /root/files/example.vrt \
            -R /usr/local/share/cwb/registry/example \
@@ -11,6 +13,7 @@ cwb-make -V EXAMPLE
 cwb-describe-corpus EXAMPLE
 
 ## Encode utopien corpus
+mkdir /corpora/data/utopien
 cwb-encode -d /corpora/data/utopien \
            -f /root/files/utopien.vrt \
            -sxB \
diff --git a/files/utopien.vrt b/files/utopien.vrt
index 74bdae1..d232827 100644
--- a/files/utopien.vrt
+++ b/files/utopien.vrt
@@ -1,6 +1,6 @@
 <?xml version='1.0' encoding='UTF8'?>
 <corpus>
-<text title="jack_london__the_iron_heel">
+<entry title="the_iron_heel" author="jack_london">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -118560,7 +118560,7 @@ eBooks	ebook	NN2	|Q4.1/Y2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="george_orwell__1984">
+<entry title="1984" author="george_orwell">
 <s>
 1984	1984	MC	|N1|T1.2|T3|
 By	by	II	|Z5|
@@ -251365,7 +251365,7 @@ as	as	CSA	|Z5|
 393	393	MC	|N1|T1.2|T3|
 </s>
 </text>
-<text title="eugen_richter__pictures_of_a_socialistic_future">
+<entry title="pictures_of_a_socialistic_future" author="eugen_richter">
 <s>
 PICTURES	picture	NN2	|C1|Q4.3|X4.1|
 OF	of	IO	|Z5|
@@ -296907,7 +296907,7 @@ ERNST	ernst	NP1	|Z99|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="ernest_callenbach__ecotopia">
+<entry title="ecotopia" author="ernest_callenbach">
 <s>
 Ernest	ernest	NP1	|Z1m|
 gallenbach	gallenbach	JJ	|Z99|
@@ -382648,7 +382648,7 @@ home	home	RL	|H4|M6|
 WILL	will	VM	|T1.1.3|
 </s>
 </text>
-<text title="karin_boye__kallocain">
+<entry title="kallocain" author="karin_boye">
 <s>
 KALLOCAIN	kallocain	VV0	|Z99|
 BY	by	II	|Z5|
@@ -462032,7 +462032,7 @@ PAIPHO	paipho	NN1	|Z99|
 Censor	censor	VV0	|Q4/S7.4-|
 </s>
 </text>
-<text title="anthony_burgess__clockwork_orange">
+<entry title="clockwork_orange" author="anthony_burgess">
 <s>
 SHEPHERD	shepherd	NP1	|F4/S2mf|
 :	PUNC	YCOL	|PUNC|
@@ -472856,7 +472856,7 @@ not	not	XX	|Z6|
 be	be	VBI	|A3+|Z5|
 </s>
 </text>
-<text title="adam_sternberg__shovel_ready">
+<entry title="shovel_ready" author="adam_sternberg">
 <s>
 Every	every	AT1	|N5.1+|
 human	human	JJ	|S2mf|
@@ -479322,7 +479322,7 @@ curse	curse	VV0	|Q2.2|A1.4-|
 Goddamn	goddamn	UH	|Z99|
 </s>
 </text>
-<text title="thomas_moore__utopia">
+<entry title="utopia" author="thomas_moore">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -534794,7 +534794,7 @@ eBooks	ebook	NN2	|Q4.1/Y2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="william_gibson__neuromancer">
+<entry title="neuromancer" author="william_gibson">
 <s>
 Neuromancer	neuromancer	NP1	|Z99|
 William	william	NP1	|Z1m|
@@ -651295,7 +651295,7 @@ why	why	RRQ	|A2.2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="mercier__memoirs_of_the_year_2500">
+<entry title="memoirs_of_the_year_2500" author="mercier">
 <s>
 Introduction	introduction	NN1	|T2+|Q4|S1.1.1|
 1LITERARY	1literary	FO	|Z99|
@@ -720473,7 +720473,7 @@ and	and	CC	|Z5|
 even	even	RR	|A13.1|
 </s>
 </text>
-<text title="henry_thomas__the_american">
+<entry title="the_american" author="henry_thomas">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -906270,7 +906270,7 @@ eBooks	ebook	NN2	|Q4.1/Y2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="michael_young__rise_of_the_meritocracy">
+<entry title="rise_of_the_meritocracy" author="michael_young">
 <s>
 The	the	AT	|Z5|
 courage	courage	NN1	|E5+/S1.2|
@@ -922466,7 +922466,7 @@ i0%	i0%	FO	|Z99|
 i	i	ZZ1	|Z5|
 </s>
 </text>
-<text title="ray_bradbury__fahrenheit_451">
+<entry title="fahrenheit_451" author="ray_bradbury">
 <s>
 FAHRENHEIT	fahrenheit	NP1	|Z99|
 451	451	MC	|N1|T1.2|T3|
@@ -988288,7 +988288,7 @@ THE	the	AT	|Z5|
 END	end	NN1	|M6|T2-|O2|
 </s>
 </text>
-<text title="edward_bellamy__looking_backward">
+<entry title="looking_backward" author="edward_bellamy">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -1093742,7 +1093742,7 @@ eBooks	ebook	NN2	|Q4.1/Y2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="isaac_asimov__i_robot">
+<entry title="i_robot" author="isaac_asimov">
 <s>
 I	i	PPIS1	|Z8mf|
 ,	PUNC	YCOM	|PUNC|
@@ -1188344,7 +1188344,7 @@ end	end	NN1	|M6|T2-|O2|
 ----	----	NN1	|Z99|
 </s>
 </text>
-<text title="philipp_k_dick__do_androids_dream_of_electric_sheep">
+<entry title="do_androids_dream_of_electric_sheep" author="philipp_k_dick">
 <s>
 Do	do	VD0	|A1.1.1|G2.2-|X9.2+|
 Androids	android	NN2	|O3|
@@ -1279301,7 +1279301,7 @@ coffee	coffee	NN1	|F2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="jewgnij_samjatin__we">
+<entry title="we" author="jewgnij_samjatin">
 <s>
 RECORD	record	VV0	|Q1.2|K3|
 ONE	one	PN1	|Z8|
@@ -1364770,7 +1364770,7 @@ prevail	prevail	VVI	|X9.2+|S7.1+|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="william_morris__news_from_nowhere">
+<entry title="news_from_nowhere" author="william_morris">
 <s>
 Project	project	NP1	|A10+|X7+|X2.6+|
 Gutenberg	gutenberg	NP1	|Z99|
@@ -1464183,7 +1464183,7 @@ William	william	NP1	|Z1m|
 Morris	morris	NP1	|Z1mf|
 </s>
 </text>
-<text title="samuel_butler__erewhon">
+<entry title="erewhon" author="samuel_butler">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -1566447,7 +1566447,7 @@ eBooks	ebook	NN2	|Q4.1/Y2|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="francis_bacon__new_atlantis">
+<entry title="new_atlantis" author="francis_bacon">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -1588246,7 +1588246,7 @@ Francis	francis	NP1	|Z1m|
 Bacon	bacon	NP1	|F1|
 </s>
 </text>
-<text title="murray_leinster__a_logic_named_joe">
+<entry title="a_logic_named_joe" author="murray_leinster">
 <s>
 A	a	AT1	|Z5|
 Logic	logic	NN1	|X2.1|S1.2.6+|N2|
@@ -1597349,7 +1597349,7 @@ hand	hand	NN1	|Z4|
 maybe	maybe	RR	|A7|
 </s>
 </text>
-<text title="mary_shelly__the_last_man">
+<entry title="the_last_man" author="mary_shelly">
 <s>
 The	the	AT	|Z5|
 Project	project	NN1	|X7+|X2.4|
@@ -1817595,7 +1817595,7 @@ LICENSE	license	NN1	|G1.1/Q1.2|S7.4+|
 ***	***	FO	|Z99|
 </s>
 </text>
-<text title="kurt_vonnegut__player_piano">
+<entry title="player_piano" author="kurt_vonnegut">
 <s>
 CONSIDER	consider	VV0	|X2.1|X2.4|X6|
 THE	the	AT	|Z5|
@@ -1957008,7 +1957008,7 @@ March	march	NPM1	|T1.3|
 .	PUNC	YSTP	|PUNC|
 </s>
 </text>
-<text title="aldous_huxley__brave_new_world">
+<entry title="brave_new_world" author="aldous_huxley">
 <s>
 BRAVE	brave	JJ	|E5+|
 NEW	new	JJ	|T3-|