Refactor string.substring usages to account for surrogate pair characters (#7206)

XingY · web-flow · commit 6a5d527e47a4 · 2025-11-18T14:47:28.000-08:00
diff --git a/api/src/org/labkey/api/data/Container.java b/api/src/org/labkey/api/data/Container.java
@@ -61,6 +61,7 @@
 import org.labkey.api.util.NetworkDrive;
 import org.labkey.api.util.PageFlowUtil;
 import org.labkey.api.util.Path;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.logging.LogHelper;
 import org.labkey.api.view.ActionURL;
 import org.labkey.api.view.FolderTab;
@@ -1594,7 +1595,7 @@ public String getContainerNoun(boolean titleCase)
         String noun = _containerType.getContainerNoun(this);
         if (titleCase)
         {
-            return noun.substring(0, 1).toUpperCase() + noun.substring(1);
+            return StringUtilsLabKey.leftSurrogatePairFriendly(noun, 1).toUpperCase() + StringUtilsLabKey.rightSurrogatePairFriendly(noun, noun.length() - 1);
         }
 
         return noun;
diff --git a/api/src/org/labkey/api/data/ExcelCellUtils.java b/api/src/org/labkey/api/data/ExcelCellUtils.java
@@ -8,6 +8,7 @@
 import org.apache.poi.ss.usermodel.CellStyle;
 import org.apache.poi.ss.usermodel.Workbook;
 import org.labkey.api.util.DateUtil;
+import org.labkey.api.util.StringUtilsLabKey;
 
 import java.io.File;
 import java.math.BigDecimal;
@@ -188,7 +189,7 @@ public static void writeCell(Cell cell, CellStyle style, int simpleType, String
                 // Check if the string is too long
                 if (s.length() > 32767)
                 {
-                    s = s.substring(0, 32762) + "...";
+                    s = StringUtilsLabKey.leftSurrogatePairFriendly(s, 32762) + "...";
                 }
                 // Ensure the row is tall enough to show the full values when there are newlines
                 int newlines = StringUtils.countMatches(s, '\n');
diff --git a/api/src/org/labkey/api/data/ExcelWriter.java b/api/src/org/labkey/api/data/ExcelWriter.java
@@ -36,6 +36,7 @@
 import org.apache.poi.ss.usermodel.Workbook;
 import org.apache.poi.ss.util.CellRangeAddress;
 import org.apache.poi.ss.util.WorkbookUtil;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.apache.poi.xssf.streaming.SXSSFSheet;
 import org.apache.poi.xssf.streaming.SXSSFWorkbook;
 import org.jetbrains.annotations.NotNull;
@@ -375,7 +376,7 @@ public void setSheetName(String sheetName)
             sheetName = "Sheet";
 
         if (sheetName.length() > 31)
-            return cleanSheetName(sheetName.substring(0, 31));
+            return cleanSheetName(StringUtilsLabKey.leftSurrogatePairFriendly(sheetName, 31));
 
         return WorkbookUtil.createSafeSheetName(sheetName, '_');
     }
diff --git a/api/src/org/labkey/api/data/SQLFragment.java b/api/src/org/labkey/api/data/SQLFragment.java
@@ -30,6 +30,7 @@
 import org.labkey.api.util.GUID;
 import org.labkey.api.util.JdbcUtil;
 import org.labkey.api.util.Pair;
+import org.labkey.api.util.StringUtilsLabKey;
 
 import java.math.BigDecimal;
 import java.math.BigInteger;
@@ -754,7 +755,7 @@ public boolean appendComment(String comment, SqlDialect dialect)
             sb.append("\n-- ");
             boolean truncated = comment.length() > 1000;
             if (truncated)
-                comment = comment.substring(0,1000);
+                comment = StringUtilsLabKey.leftSurrogatePairFriendly(comment, 1000);
             sb.append(comment);
             if (StringUtils.countMatches(comment, "'")%2==1)
                 sb.append("'");
diff --git a/api/src/org/labkey/api/data/TSVWriter.java b/api/src/org/labkey/api/data/TSVWriter.java
@@ -20,6 +20,7 @@
 import org.junit.Assert;
 import org.junit.Test;
 import org.labkey.api.util.FileUtil;
+import org.labkey.api.util.StringUtilsLabKey;
 
 import java.io.IOException;
 import java.io.PrintWriter;
@@ -109,7 +110,7 @@ public void setFilenamePrefix(String filenamePrefix)
         _filenamePrefix = badChars.matcher(filenamePrefix).replaceAll("_");
 
         if (_filenamePrefix.length() > 30)
-            _filenamePrefix = _filenamePrefix.substring(0, 30);
+            _filenamePrefix = StringUtilsLabKey.leftSurrogatePairFriendly(_filenamePrefix, 30);
     }
 
     public void setDelimiterCharacter(char delimiter)
diff --git a/api/src/org/labkey/api/data/dialect/StatementWrapper.java b/api/src/org/labkey/api/data/dialect/StatementWrapper.java
@@ -34,6 +34,7 @@
 import org.labkey.api.util.DebugInfoDumper;
 import org.labkey.api.util.ExceptionUtil;
 import org.labkey.api.util.MemTracker;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.view.ViewServlet;
 
 import java.io.InputStream;
@@ -2876,7 +2877,7 @@ else if (o instanceof String)
                     else
                         value = String.valueOf(o);
                     if (value.length() > 100)
-                        value = value.substring(0, 100) + ". . .";
+                        value = StringUtilsLabKey.leftSurrogatePairFriendly(value, 100) + ". . .";
                     logEntry.append("\n    --[").append(i).append("] ");
                     logEntry.append(value);
                     Class<?> c = null==o ? null : o.getClass();
diff --git a/api/src/org/labkey/api/exp/OntologyManager.java b/api/src/org/labkey/api/exp/OntologyManager.java
@@ -65,6 +65,7 @@
 import org.labkey.api.util.HtmlString;
 import org.labkey.api.util.HtmlStringBuilder;
 import org.labkey.api.util.Pair;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.ResultSetUtil;
 import org.labkey.api.util.TestContext;
 import org.labkey.api.view.HttpView;
@@ -767,7 +768,7 @@ public static boolean validateProperty(List<? extends IPropertyValidator> valida
         int stringLength = value == null ? 0 : value.toString().length();
         if (value != null && prop.isStringType() && stringLength > stringLengthLimit)
         {
-            String s = stringLength < 100 ? value.toString() : value.toString().substring(0, 100);
+            String s = stringLength <= 100 ? value.toString() : StringUtilsLabKey.leftSurrogatePairFriendly(value.toString(), 100);
             errors.add(new PropertyValidationError("Field '" + prop.getName() + "' is limited to " + stringLengthLimit + " characters, but the value is " + stringLength + " characters. (The value starts with '" + s + "...')", prop.getName()));
             ret = false;
         }
diff --git a/api/src/org/labkey/api/jsp/LabKeyJspWriter.java b/api/src/org/labkey/api/jsp/LabKeyJspWriter.java
@@ -20,6 +20,7 @@
 import org.labkey.api.util.DOM;
 import org.labkey.api.util.HelpTopic;
 import org.labkey.api.util.SafeToRender;
+import org.labkey.api.util.StringUtilsLabKey;
 
 import jakarta.servlet.jsp.JspWriter;
 import java.io.IOException;
@@ -44,7 +45,7 @@ private String truncateAndQuote(String s)
         {
             return null;
         }
-        return "'" + (s.length() < 50 ? s : (s.substring(0, 50) + "...")) + "'";
+        return "'" + (s.length() < 50 ? s : (StringUtilsLabKey.leftSurrogatePairFriendly(s, 50) + "...")) + "'";
     }
 
     @Override
diff --git a/api/src/org/labkey/api/util/MemTracker.java b/api/src/org/labkey/api/util/MemTracker.java
@@ -138,7 +138,7 @@ public String getClassName()
         public String getObjectSummary()
         {
             String desc = getObjectDescription();
-            return desc.length() > 50 ? desc.substring(0, 50) + "..." : desc;
+            return desc.length() > 50 ? StringUtilsLabKey.leftSurrogatePairFriendly(desc, 50) + "..." : desc;
         }
 
         public boolean hasShortSummary()
diff --git a/core/src/org/labkey/core/admin/AdminController.java b/core/src/org/labkey/core/admin/AdminController.java
@@ -9796,7 +9796,7 @@ public void validateCommand(TabActionForm form, Errors errors)
                 }
 
                 if (name.length() > 50)
-                    name = name.substring(0, 50).trim();
+                    name = StringUtilsLabKey.leftSurrogatePairFriendly(name, 50).trim();
 
                 CaseInsensitiveHashMap<Portal.PortalPage> pages = new CaseInsensitiveHashMap<>(Portal.getPages(tabContainer, true));
                 CaseInsensitiveHashMap<FolderTab> folderTabMap = new CaseInsensitiveHashMap<>();
@@ -9850,7 +9850,7 @@ public ApiResponse execute(TabActionForm form, BindException errors)
             // The name, which shows up on the url, is trimmed to 50 characters. The caption, which is derived from the
             // name, and is editable, is allowed to be 64 characters.
             if (name.length() > 50)
-                name = name.substring(0, 50).trim();
+                name = StringUtilsLabKey.leftSurrogatePairFriendly(name, 50).trim();
 
             Portal.saveParts(container, name);
             Portal.addProperty(container, name, Portal.PROP_CUSTOMTAB);
diff --git a/experiment/src/org/labkey/experiment/api/AbstractRunInput.java b/experiment/src/org/labkey/experiment/api/AbstractRunInput.java
@@ -18,6 +18,7 @@
 import org.jetbrains.annotations.Nullable;
 import org.labkey.api.exp.IdentifiableBase;
 import org.labkey.api.exp.Lsid;
+import org.labkey.api.util.StringUtilsLabKey;
 
 import java.util.Objects;
 
@@ -65,7 +66,7 @@ public void setRole(@Nullable String role)
         // so truncate here if needed to prevent a SQLException later
         if (role.length() > 50)
         {
-            role = role.substring(0, 49);
+            role = StringUtilsLabKey.leftSurrogatePairFriendly(role, 49);
         }
         _role = role;
     }
diff --git a/experiment/src/org/labkey/experiment/api/ExpDataImpl.java b/experiment/src/org/labkey/experiment/api/ExpDataImpl.java
@@ -69,6 +69,7 @@
 import org.labkey.api.util.NetworkDrive;
 import org.labkey.api.util.Pair;
 import org.labkey.api.util.Path;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.URLHelper;
 import org.labkey.api.util.InputBuilder;
 import org.labkey.api.view.ActionURL;
@@ -796,7 +797,7 @@ private static void appendTokens(StringBuilder sb, Collection<String> toks)
         if (toks.isEmpty())
             return;
 
-        sb.append(toks.stream().map(s -> s.length() > 30 ? s.substring(0, 30) + "\u2026" : s).collect(Collectors.joining(", "))).append("\n");
+        sb.append(toks.stream().map(s -> s.length() > 30 ? StringUtilsLabKey.leftSurrogatePairFriendly(s, 30) + "\u2026" : s).collect(Collectors.joining(", "))).append("\n");
     }
 
     private static class ExpDataResource extends SimpleDocumentResource
diff --git a/mothership/src/org/labkey/mothership/MothershipManager.java b/mothership/src/org/labkey/mothership/MothershipManager.java
@@ -41,6 +41,7 @@
 import org.labkey.api.util.JsonUtil;
 import org.labkey.api.util.MothershipReport;
 import org.labkey.api.util.ReentrantLockWithName;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.logging.LogHelper;
 
 import java.io.IOException;
@@ -109,19 +110,19 @@ public void insertException(ExceptionStackTrace stackTrace, ExceptionReport repo
 
             String url = report.getUrl();
             if (null != url && url.length() > 512)
-                report.setURL(url.substring(0, 506) + "...");
+                report.setURL(StringUtilsLabKey.leftSurrogatePairFriendly(url, 506) + "...");
 
             String referrerURL = report.getReferrerURL();
             if (null != referrerURL && referrerURL.length() > 512)
-                report.setReferrerURL(referrerURL.substring(0, 506) + "...");
+                report.setReferrerURL(StringUtilsLabKey.leftSurrogatePairFriendly(referrerURL, 506) + "...");
 
             String browser = report.getBrowser();
             if (null != browser && browser.length() > 100)
                 report.setBrowser(browser.substring(0,90) + "...");
 
             String exceptionMessage = report.getExceptionMessage();
             if (null != exceptionMessage && exceptionMessage.length() > 1000)
-                report.setExceptionMessage(exceptionMessage.substring(0,990) + "...");
+                report.setExceptionMessage(StringUtilsLabKey.leftSurrogatePairFriendly(exceptionMessage, 990) + "...");
 
             String actionName = report.getPageflowAction();
             if (null != actionName && actionName.length() > 40)
diff --git a/pipeline/src/org/labkey/pipeline/api/WorkDirectoryRemote.java b/pipeline/src/org/labkey/pipeline/api/WorkDirectoryRemote.java
@@ -150,7 +150,7 @@ public WorkDirectory createWorkDirectory(String jobId, FileAnalysisJobSupport su
                         // Don't let the total path get too long - Windows doesn't like paths longer than 255 characters
                         // so if there's a ridiculously long file name, we don't want to duplicate its name in the
                         // directory too
-                        name = name.substring(0, 9);
+                        name = StringUtilsLabKey.leftSurrogatePairFriendly(name, 9);
                     }
                     else if (name.length() < 3)
                     {
diff --git a/query/src/org/labkey/query/controllers/QueryController.java b/query/src/org/labkey/query/controllers/QueryController.java
@@ -235,6 +235,7 @@
 import org.labkey.api.util.ResponseHelper;
 import org.labkey.api.util.ReturnURLString;
 import org.labkey.api.util.StringExpression;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.TestContext;
 import org.labkey.api.util.URLHelper;
 import org.labkey.api.util.UnexpectedException;
@@ -2134,7 +2135,7 @@ public Object execute(ExportQueriesForm form, BindException errors) throws Excep
                         throw new IllegalArgumentException("Cannot create sheet names from overlapping query names.");
                     for (int i = 0; i < queryForms.size(); i++)
                     {
-                        sheetNames.put(entry.getValue().get(i), name.substring(0, name.length() - countLength) + "(" + i + ")");
+                        sheetNames.put(entry.getValue().get(i), StringUtilsLabKey.leftSurrogatePairFriendly(name, name.length() - countLength) + "(" + i + ")");
                     }
                 }
                 else
diff --git a/search/src/org/labkey/search/SearchController.java b/search/src/org/labkey/search/SearchController.java
@@ -58,6 +58,7 @@
 import org.labkey.api.util.HtmlStringBuilder;
 import org.labkey.api.util.Path;
 import org.labkey.api.util.ResponseHelper;
+import org.labkey.api.util.StringUtilsLabKey;
 import org.labkey.api.util.URLHelper;
 import org.labkey.api.util.logging.LogHelper;
 import org.labkey.api.view.ActionURL;
@@ -1126,7 +1127,7 @@ public static void audit(@Nullable User user, @Nullable Container c, String quer
             c = ContainerManager.getRoot();
 
         if (query.length() > 200)
-            query = query.substring(0, 197) + "...";
+            query = StringUtilsLabKey.leftSurrogatePairFriendly(query, 197) + "...";
 
         SearchAuditProvider.SearchAuditEvent event = new SearchAuditProvider.SearchAuditEvent(c, comment);
         event.setQuery(query);

Original file line number	Diff line number	Diff line change
`@@ -20,6 +20,7 @@`
`20`	`20`	`import org.labkey.api.util.DOM;`
`21`	`21`	`import org.labkey.api.util.HelpTopic;`
`22`	`22`	`import org.labkey.api.util.SafeToRender;`
	`23`	`+import org.labkey.api.util.StringUtilsLabKey;`
`23`	`24`
`24`	`25`	`import jakarta.servlet.jsp.JspWriter;`
`25`	`26`	`import java.io.IOException;`
`@@ -44,7 +45,7 @@ private String truncateAndQuote(String s)`
`44`	`45`	`{`
`45`	`46`	`return null;`
`46`	`47`	`}`
`47`		`- return "'" + (s.length() < 50 ? s : (s.substring(0, 50) + "...")) + "'";`
	`48`	`+ return "'" + (s.length() < 50 ? s : (StringUtilsLabKey.leftSurrogatePairFriendly(s, 50) + "...")) + "'";`
`48`	`49`	`}`
`49`	`50`
`50`	`51`	`@Override`
Original file line number	Diff line number	Diff line change
`@@ -138,7 +138,7 @@ public String getClassName()`
`138`	`138`	`public String getObjectSummary()`
`139`	`139`	`{`
`140`	`140`	`String desc = getObjectDescription();`
`141`		`- return desc.length() > 50 ? desc.substring(0, 50) + "..." : desc;`
	`141`	`+ return desc.length() > 50 ? StringUtilsLabKey.leftSurrogatePairFriendly(desc, 50) + "..." : desc;`
`142`	`142`	`}`
`143`	`143`
`144`	`144`	`public boolean hasShortSummary()`