1 | #!/bin/sh |
---|
2 | # Licensed to the Apache Software Foundation (ASF) under one or more |
---|
3 | # contributor license agreements. See the NOTICE file distributed with |
---|
4 | # this work for additional information regarding copyright ownership. |
---|
5 | # The ASF licenses this file to You under the Apache License, Version 2.0 |
---|
6 | # (the "License"); you may not use this file except in compliance with |
---|
7 | # the License. You may obtain a copy of the License at |
---|
8 | # |
---|
9 | # http://www.apache.org/licenses/LICENSE-2.0 |
---|
10 | # |
---|
11 | # Unless required by applicable law or agreed to in writing, software |
---|
12 | # distributed under the License is distributed on an "AS IS" BASIS, |
---|
13 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
14 | # See the License for the specific language governing permissions and |
---|
15 | # limitations under the License. |
---|
16 | |
---|
17 | #Test script to tell if the server is accepting UTF-8 |
---|
18 | #The python writer currently escapes non-ascii chars, so it's good for testing |
---|
19 | |
---|
20 | URL=http://localhost:8983/solr |
---|
21 | |
---|
22 | if [ ! -z $1 ]; then |
---|
23 | URL=$1 |
---|
24 | fi |
---|
25 | |
---|
26 | curl "$URL/select?q=hello¶ms=explicit&wt=python" 2> /dev/null | grep 'hello' > /dev/null 2>&1 |
---|
27 | if [ $? = 0 ]; then |
---|
28 | echo "Solr server is up." |
---|
29 | else |
---|
30 | echo "ERROR: Solr is not up." |
---|
31 | exit 1 |
---|
32 | fi |
---|
33 | |
---|
34 | curl "$URL/select?q=h%C3%A9llo&echoParams=explicit&wt=python" 2> /dev/null | grep 'h\\u00e9llo' > /dev/null 2>&1 |
---|
35 | if [ $? = 0 ]; then |
---|
36 | echo "HTTP GET is accepting UTF-8" |
---|
37 | else |
---|
38 | echo "ERROR: HTTP GET is not accepting UTF-8" |
---|
39 | fi |
---|
40 | |
---|
41 | curl $URL/select --data-binary 'q=h%C3%A9llo&echoParams=explicit&wt=python' -H 'Content-type:application/x-www-form-urlencoded; charset=UTF-8' 2> /dev/null | grep 'h\\u00e9llo' > /dev/null 2>&1 |
---|
42 | if [ $? = 0 ]; then |
---|
43 | echo "HTTP POST is accepting UTF-8" |
---|
44 | else |
---|
45 | echo "ERROR: HTTP POST is not accepting UTF-8" |
---|
46 | fi |
---|
47 | |
---|
48 | curl $URL/select --data-binary 'q=h%C3%A9llo&echoParams=explicit&wt=python' 2> /dev/null | grep 'h\\u00e9llo' > /dev/null 2>&1 |
---|
49 | if [ $? = 0 ]; then |
---|
50 | echo "HTTP POST defaults to UTF-8" |
---|
51 | else |
---|
52 | echo "HTTP POST does not default to UTF-8" |
---|
53 | fi |
---|
54 | |
---|
55 | |
---|
56 | #A unicode character outside of the BMP (a circle with an x inside) |
---|
57 | CHAR="ð" |
---|
58 | CODEPOINT='0x10308' |
---|
59 | #URL encoded UTF8 of the codepoint |
---|
60 | URL_UTF8='%F0%90%8C%88' |
---|
61 | #expected return of the python writer (currently uses UTF-16 surrogates) |
---|
62 | EXPECTED='\\ud800\\udf08' |
---|
63 | |
---|
64 | curl "$URL/select?q=$URL_UTF8&echoParams=explicit&wt=python" 2> /dev/null | grep $EXPECTED > /dev/null 2>&1 |
---|
65 | if [ $? = 0 ]; then |
---|
66 | echo "HTTP GET is accepting UTF-8 beyond the basic multilingual plane" |
---|
67 | else |
---|
68 | echo "ERROR: HTTP GET is not accepting UTF-8 beyond the basic multilingual plane" |
---|
69 | fi |
---|
70 | |
---|
71 | curl $URL/select --data-binary "q=$URL_UTF8&echoParams=explicit&wt=python" -H 'Content-type:application/x-www-form-urlencoded; charset=UTF-8' 2> /dev/null | grep $EXPECTED > /dev/null 2>&1 |
---|
72 | if [ $? = 0 ]; then |
---|
73 | echo "HTTP POST is accepting UTF-8 beyond the basic multilingual plane" |
---|
74 | else |
---|
75 | echo "ERROR: HTTP POST is not accepting UTF-8 beyond the basic multilingual plane" |
---|
76 | fi |
---|
77 | |
---|
78 | curl "$URL/select?q=$URL_UTF8&echoParams=explicit&wt=python" --data-binary '' 2> /dev/null | grep $EXPECTED > /dev/null 2>&1 |
---|
79 | if [ $? = 0 ]; then |
---|
80 | echo "HTTP POST + URL params is accepting UTF-8 beyond the basic multilingual plane" |
---|
81 | else |
---|
82 | echo "ERROR: HTTP POST + URL params is not accepting UTF-8 beyond the basic multilingual plane" |
---|
83 | fi |
---|
84 | |
---|
85 | #curl "$URL/select?q=$URL_UTF8&echoParams=explicit&wt=json" 2> /dev/null | od -tx1 -w1000 | sed 's/ //g' | grep 'f4808198' > /dev/null 2>&1 |
---|
86 | curl "$URL/select?q=$URL_UTF8&echoParams=explicit&wt=json" 2> /dev/null | grep "$CHAR" > /dev/null 2>&1 |
---|
87 | if [ $? = 0 ]; then |
---|
88 | echo "Response correctly returns UTF-8 beyond the basic multilingual plane" |
---|
89 | else |
---|
90 | echo "ERROR: Response can't return UTF-8 beyond the basic multilingual plane" |
---|
91 | fi |
---|
92 | |
---|
93 | |
---|