honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Docs: Use splitOnToken instead of custom function (#48408) (#54364) 

Painless ingest example uses a custom split function but
new splitOnToken function was added in 7.2

Backport of: 0c52a92
This commit is contained in:
Stuart Tettemer 2020-03-27 15:04:27 -06:00 committed by GitHub
parent 2ccddbfa88
commit 30c56087fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 33 additions and 104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
docs/painless/painless-contexts/painless-ingest-processor-context.asciidoc
View File

@ -57,119 +57,68 @@ result in a `datetime` field.
[source,Painless]
----
String[] split(String s, char d) { <1>
int count = 0;
for (char c : s.toCharArray()) { <2>
if (c == d) {
++count;
}
}
if (count == 0) {
return new String[] {s}; <3>
}
String[] r = new String[count + 1]; <4>
int i0 = 0, i1 = 0;
count = 0;
for (char c : s.toCharArray()) { <5>
if (c == d) {
r[count++] = s.substring(i0, i1);
i0 = i1 + 1;
}
++i1;
}
r[count] = s.substring(i0, i1); <6>
return r;
}
String[] dateSplit = split(ctx.date, (char)"-"); <7>
String[] dateSplit = ctx.date.splitOnToken("-"); <1>
String year = dateSplit[0].trim();
String month = dateSplit[1].trim();
if (month.length() == 1) { <8>
if (month.length() == 1) { <2>
month = "0" + month;
}
String day = dateSplit[2].trim();
if (day.length() == 1) { <9>
if (day.length() == 1) { <3>
day = "0" + day;
}
boolean pm = ctx.time.substring(ctx.time.length() - 2).equals("PM"); <10>
String[] timeSplit = split(
ctx.time.substring(0, ctx.time.length() - 2), (char)":"); <11>
boolean pm = ctx.time.substring(ctx.time.length() - 2).equals("PM"); <4>
String[] timeSplit = ctx.time.substring(0,
ctx.time.length() - 2).splitOnToken(":"); <5>
int hours = Integer.parseInt(timeSplit[0].trim());
int minutes = Integer.parseInt(timeSplit[1].trim());
if (pm) { <12>
if (pm) { <6>
hours += 12;
}
String dts = year + "-" + month + "-" + day + "T" +
(hours < 10 ? "0" + hours : "" + hours) + ":" +
(minutes < 10 ? "0" + minutes : "" + minutes) +
":00+08:00"; <13>
":00+08:00"; <7>
ZonedDateTime dt = ZonedDateTime.parse(
dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); <14>
ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L; <15>
dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); <8>
ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L; <9>
----
<1> Creates a `split` <<painless-functions, function>> to split a
<<string-type, `String`>> type value using a <<primitive-types, `char`>>
type value as the delimiter. This is useful for handling the necessity of
pulling out the individual pieces of the date and time `Strings` from the
original seat data.
<2> The first pass through each `char` in the `String` collects how many new
`Strings` the original is split into.
<3> Returns the original `String` if there are no instances of the delimiting
`char`.
<4> Creates an <<array-type, array type>> value to collect the split `Strings`
into based on the number of `char` delimiters found in the first pass.
<5> The second pass through each `char` in the `String` collects each split
substring into an array type value of `Strings`.
<6> Collects the last substring into the array type value of `Strings`.
<7> Uses the `split` function to separate the date `String` from the seat data
into year, month, and day `Strings`.
<1> Uses the `splitOnToken` function to separate the date `String` from the
seat data into year, month, and day `Strings`.
Note::
* The use of a `String` type value to `char` type value
<<string-character-casting, cast>> as part of the second argument since
character literals do not exist.
* The use of the `ctx` ingest processor context variable to retrieve the
data from the `date` field.
<8> Appends the <<string-literals, string literal>> `"0"` value to a single
<2> Appends the <<string-literals, string literal>> `"0"` value to a single
digit month since the format of the seat data allows for this case.
<9> Appends the <<string-literals, string literal>> `"0"` value to a single
<3> Appends the <<string-literals, string literal>> `"0"` value to a single
digit day since the format of the seat data allows for this case.
<10> Sets the <<primitive-types, `boolean type`>>
<4> Sets the <<primitive-types, `boolean type`>>
<<painless-variables, variable>> to `true` if the time `String` is a time
in the afternoon or evening.
Note::
* The use of the `ctx` ingest processor context variable to retrieve the
data from the `time` field.
<11> Uses the `split` function to separate the time `String` from the seat data
into hours and minutes `Strings`.
<5> Uses the `splitOnToken` function to separate the time `String` from the
seat data into hours and minutes `Strings`.
Note::
* The use of the `substring` method to remove the `AM` or `PM` portion of
the time `String`.
* The use of a `String` type value to `char` type value
<<string-character-casting, cast>> as part of the second argument since
character literals do not exist.
* The use of the `ctx` ingest processor context variable to retrieve the
data from the `date` field.
<12> If the time `String` is an afternoon or evening value adds the
<6> If the time `String` is an afternoon or evening value adds the
<<integer-literals, integer literal>> `12` to the existing hours to move to
a 24-hour based time.
<13> Builds a new time `String` that is parsable using existing API methods.
<14> Creates a `ZonedDateTime` <<reference-types, reference type>> value by using
<7> Builds a new time `String` that is parsable using existing API methods.
<8> Creates a `ZonedDateTime` <<reference-types, reference type>> value by using
the API method `parse` to parse the new time `String`.
<15> Sets the datetime field `datetime` to the number of milliseconds retrieved
<9> Sets the datetime field `datetime` to the number of milliseconds retrieved
from the API method `getLong`.
Note::
* The use of the `ctx` ingest processor context variable to set the field
@ -186,7 +135,7 @@ PUT /_ingest/pipeline/seats
"processors": [
{
"script": {
"source": "String[] split(String s, char d) { int count = 0; for (char c : s.toCharArray()) { if (c == d) { ++count; } } if (count == 0) { return new String[] {s}; } String[] r = new String[count + 1]; int i0 = 0, i1 = 0; count = 0; for (char c : s.toCharArray()) { if (c == d) { r[count++] = s.substring(i0, i1); i0 = i1 + 1; } ++i1; } r[count] = s.substring(i0, i1); return r; } String[] dateSplit = split(ctx.date, (char)\"-\"); String year = dateSplit[0].trim(); String month = dateSplit[1].trim(); if (month.length() == 1) { month = \"0\" + month; } String day = dateSplit[2].trim(); if (day.length() == 1) { day = \"0\" + day; } boolean pm = ctx.time.substring(ctx.time.length() - 2).equals(\"PM\"); String[] timeSplit = split(ctx.time.substring(0, ctx.time.length() - 2), (char)\":\"); int hours = Integer.parseInt(timeSplit[0].trim()); int minutes = Integer.parseInt(timeSplit[1].trim()); if (pm) { hours += 12; } String dts = year + \"-\" + month + \"-\" + day + \"T\" + (hours < 10 ? \"0\" + hours : \"\" + hours) + \":\" + (minutes < 10 ? \"0\" + minutes : \"\" + minutes) + \":00+08:00\"; ZonedDateTime dt = ZonedDateTime.parse(dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L;"
"source": "String[] dateSplit = ctx.date.splitOnToken('-'); String year = dateSplit[0].trim(); String month = dateSplit[1].trim(); if (month.length() == 1) { month = '0' + month; } String day = dateSplit[2].trim(); if (day.length() == 1) { day = '0' + day; } boolean pm = ctx.time.substring(ctx.time.length() - 2).equals('PM'); String[] timeSplit = ctx.time.substring(0, ctx.time.length() - 2).splitOnToken(':'); int hours = Integer.parseInt(timeSplit[0].trim()); int minutes = Integer.parseInt(timeSplit[1].trim()); if (pm) { hours += 12; } String dts = year + '-' + month + '-' + day + 'T' + (hours < 10 ? '0' + hours : '' + hours) + ':' + (minutes < 10 ? '0' + minutes : '' + minutes) + ':00+08:00'; ZonedDateTime dt = ZonedDateTime.parse(dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L;"
}
}
]

42
modules/lang-painless/src/test/java/org/elasticsearch/painless/ContextExampleTests.java
View File

@ -248,7 +248,7 @@ public class ContextExampleTests extends ScriptTestCase {
"processors": [
{
"script": {
"source": "String[] split(String s, char d) { int count = 0; for (char c : s.toCharArray()) { if (c == d) { ++count; } } if (count == 0) { return new String[] {s}; } String[] r = new String[count + 1]; int i0 = 0, i1 = 0; count = 0; for (char c : s.toCharArray()) { if (c == d) { r[count++] = s.substring(i0, i1); i0 = i1 + 1; } ++i1; } r[count] = s.substring(i0, i1); return r; } String[] dateSplit = split(ctx.date, (char)\"-\"); String year = dateSplit[0].trim(); String month = dateSplit[1].trim(); if (month.length() == 1) { month = \"0\" + month; } String day = dateSplit[2].trim(); if (day.length() == 1) { day = \"0\" + day; } boolean pm = ctx.time.substring(ctx.time.length() - 2).equals(\"PM\"); String[] timeSplit = split(ctx.time.substring(0, ctx.time.length() - 2), (char)\":\"); int hours = Integer.parseInt(timeSplit[0].trim()); int minutes = Integer.parseInt(timeSplit[1].trim()); if (pm) { hours += 12; } String dts = year + \"-\" + month + \"-\" + day + \"T\" + (hours < 10 ? \"0\" + hours : \"\" + hours) + \":\" + (minutes < 10 ? \"0\" + minutes : \"\" + minutes) + \":00+08:00\"; ZonedDateTime dt = ZonedDateTime.parse(dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L;"
"source": "String[] dateSplit = ctx.date.splitOnToken('-'); String year = dateSplit[0].trim(); String month = dateSplit[1].trim(); if (month.length() == 1) { month = '0' + month; } String day = dateSplit[2].trim(); if (day.length() == 1) { day = '0' + day; } boolean pm = ctx.time.substring(ctx.time.length() - 2).equals('PM'); String[] timeSplit = ctx.time.substring(0, ctx.time.length() - 2).splitOnToken(':'); int hours = Integer.parseInt(timeSplit[0].trim()); int minutes = Integer.parseInt(timeSplit[1].trim()); if (pm) { hours += 12; } String dts = year + '-' + month + '-' + day + 'T' + (hours < 10 ? '0' + hours : '' + hours) + ':' + (minutes < 10 ? '0' + minutes : '' + minutes) + ':00+08:00'; ZonedDateTime dt = ZonedDateTime.parse(dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME); ctx.datetime = dt.getLong(ChronoField.INSTANT_SECONDS)*1000L;"
}
}
]
@ -259,31 +259,8 @@ public class ContextExampleTests extends ScriptTestCase {
public void testIngestProcessorScript() {
assertEquals(1535785200000L,
exec("String[] split(String s, char d) {" +
" int count = 0;" +
" for (char c : s.toCharArray()) {" +
" if (c == d) {" +
" ++count;" +
" }" +
" }" +
" if (count == 0) {" +
" return new String[] {s};" +
" }" +
" String[] r = new String[count + 1];" +
" int i0 = 0, i1 = 0;" +
" count = 0;" +
" for (char c : s.toCharArray()) {" +
" if (c == d) {" +
" r[count++] = s.substring(i0, i1);" +
" i0 = i1 + 1;" +
" }" +
" ++i1;" +
" }" +
" r[count] = s.substring(i0, i1);" +
" return r;" +
"}" +
"def x = ['date': '2018-9-1', 'time': '3:00 PM'];" +
"String[] dateSplit = split(x.date, (char)'-');" +
exec("def x = ['date': '2018-9-1', 'time': '3:00 PM'];" +
"String[] dateSplit = x.date.splitOnToken('-');" +
"String year = dateSplit[0].trim();" +
"String month = dateSplit[1].trim();" +
"if (month.length() == 1) {" +
@ -294,15 +271,18 @@ public class ContextExampleTests extends ScriptTestCase {
" day = '0' + day;" +
"}" +
"boolean pm = x.time.substring(x.time.length() - 2).equals('PM');" +
"String[] timeSplit = split(x.time.substring(0, x.time.length() - 2), (char)':');" +
"String[] timeSplit = x.time.substring(0, x.time.length() - 2).splitOnToken(':');" +
"int hours = Integer.parseInt(timeSplit[0].trim());" +
"String minutes = timeSplit[1].trim();" +
"int minutes = Integer.parseInt(timeSplit[1].trim());" +
"if (pm) {" +
" hours += 12;" +
"}" +
"String dts = year + '-' + month + '-' + day + " +
"'T' + (hours < 10 ? '0' + hours : '' + hours) + ':' + minutes + ':00+08:00';" +
"ZonedDateTime dt = ZonedDateTime.parse(dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME);" +
"String dts = year + '-' + month + '-' + day + 'T' +" +
" (hours < 10 ? '0' + hours : '' + hours) + ':' +" +
" (minutes < 10 ? '0' + minutes : '' + minutes) +" +
" ':00+08:00';" +
"ZonedDateTime dt = ZonedDateTime.parse(" +
" dts, DateTimeFormatter.ISO_OFFSET_DATE_TIME);" +
"return dt.getLong(ChronoField.INSTANT_SECONDS) * 1000L"
)
);