Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Browse files

rename properties files to not conflict

  • Loading branch information...
commit e72d5e0b148af7105317d159b43c1b82c3e3c301 1 parent 8da47da
@DallanQ authored
View
2  AUTHORS
@@ -6,7 +6,7 @@ names-eval/src/main/resources/AncestrySurnamePairs.csv
names-eval/src/main/resources/BorderSurnamePairs.csv
names-eval/src/main/resources/givenname_ancestry.txt (generated from AncestryGivennamePairs.csv)
names-eval/src/main/resources/surname_ancestry.txt (generated from AncestrySurnamePairs.csv)
-names-search/src/main/resources/normalizer.properties (edited by Dallan Quass)
+names-search/src/main/resources/name-normalizer.properties (edited by Dallan Quass)
names-eval/src/main/resources/givenname_nicknames.txt (edited by Dallan Quass)
We also thank WeRelate users for providing the following data files
View
4 README.md
@@ -37,7 +37,7 @@ provided by Ancestry, unprefixed roots need to be included in searches for a
prefixed surname, and vice-versa. But determining whether a name is prefixed is
not easy. That is, Vandyke and Ohare are prefixed, but Vance and Olson are not.
This table attempts to identify common prefixed surnames. Rare surnames use
-the prefix list in _searcher.properties_ to estimate whether they are prefixed.
+the prefix list in _name-searcher.properties_ to estimate whether they are prefixed.
* _givenname\_similar\_names.csv_ is a table of variants for the 70,000
most-frequent given names in Ancestry.com's database.
@@ -307,11 +307,13 @@ Change history
==============
Mar 2012 - v1.1
+
* distinguish between computer variants and confirmed variants
* new csv file format
* csv files moved from github project to separate download
Dec 2011 - v1.0
+
* initial commit
Roadmap
View
7 search/src/main/java/org/folg/names/search/Normalizer.java
@@ -62,7 +62,7 @@ private Normalizer() {
// read properties file
try {
Properties props = new Properties();
- props.load(new InputStreamReader(getClass().getClassLoader().getResourceAsStream("normalizer.properties"), "UTF8"));
+ props.load(new InputStreamReader(getClass().getClassLoader().getResourceAsStream("name-normalizer.properties"), "UTF8"));
maxTerms = Integer.parseInt(props.getProperty("maxTerms"));
delimiters = new HashSet<Character>();
for (char c : props.getProperty("delimiterList").toCharArray()) {
@@ -82,7 +82,7 @@ private Normalizer() {
abbreviatedGivenNames.put(fields[0], fields[1]);
}
} catch (IOException e) {
- throw new RuntimeException("normalizer.properties not found");
+ throw new RuntimeException("name-normalizer.properties not found");
}
}
@@ -163,6 +163,9 @@ else if (c >= 'A' && c <= 'Z') {
else if (c >= 'a' && c <= 'z') {
buf.append(c);
}
+ else if (allowWildcards && (c == '?' || c == '*')) {
+ buf.append(c);
+ }
else if (Character.isLetter(c)) {
// ignore letters > U+0250; they're generally from scripts that don't map well to roman letters
// ignore 186,170: superscript o and a used in spanish numbers: 1^a and 2^o
View
2  search/src/main/java/org/folg/names/search/Searcher.java
@@ -129,7 +129,7 @@ private Searcher(final boolean isSurname) {
try {
// read properties
Properties props = new Properties();
- props.load(new InputStreamReader(getClass().getClassLoader().getResourceAsStream("searcher.properties"), "UTF8"));
+ props.load(new InputStreamReader(getClass().getClassLoader().getResourceAsStream("name-searcher.properties"), "UTF8"));
if (isSurname) {
surnameProbablePrefixes = Arrays.asList(props.getProperty("surnameProbablePrefixList").split(","));
surnameProbablePrefixesStart = new HashSet<String>(); // let's optimize the probable prefixes lookup just a bit
View
0  search/src/main/resources/normalizer.properties → search/src/main/resources/name-normalizer.properties
File renamed without changes
View
0  search/src/main/resources/searcher.properties → search/src/main/resources/name-searcher.properties
File renamed without changes
Please sign in to comment.
Something went wrong with that request. Please try again.