| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "https://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
| <html xmlns="http://www.w3.org/1999/xhtml" lang="en-US"> |
| <head> |
| <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> |
| <meta http-equiv="X-UA-Compatible" content="IE=11"/> |
| <meta name="generator" content="Doxygen 1.9.8"/> |
| <meta name="viewport" content="width=device-width, initial-scale=1"/> |
| <title>iceberg-cpp: iceberg::StringUtils Class Reference</title> |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="dynsections.js"></script> |
| <link href="search/search.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="search/searchdata.js"></script> |
| <script type="text/javascript" src="search/search.js"></script> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div, it is closed by doxygen! --> |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr id="projectrow"> |
| <td id="projectalign"> |
| <div id="projectname">iceberg-cpp |
| </div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.9.8 --> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:d3d9a9a6595521f9666a5e94cc830dab83b65699&dn=expat.txt MIT */ |
| var searchBox = new SearchBox("searchBox", "search/",'.html'); |
| /* @license-end */ |
| </script> |
| <script type="text/javascript" src="menudata.js"></script> |
| <script type="text/javascript" src="menu.js"></script> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:d3d9a9a6595521f9666a5e94cc830dab83b65699&dn=expat.txt MIT */ |
| $(function() { |
| initMenu('',true,false,'search.php','Search'); |
| $(document).ready(function() { init_search(); }); |
| }); |
| /* @license-end */ |
| </script> |
| <div id="main-nav"></div> |
| <!-- window showing the filter options --> |
| <div id="MSearchSelectWindow" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| onkeydown="return searchBox.OnSearchSelectKey(event)"> |
| </div> |
| |
| <!-- iframe showing the search results (closed by default) --> |
| <div id="MSearchResultsWindow"> |
| <div id="MSearchResults"> |
| <div class="SRPage"> |
| <div id="SRIndex"> |
| <div id="SRResults"></div> |
| <div class="SRStatus" id="Loading">Loading...</div> |
| <div class="SRStatus" id="Searching">Searching...</div> |
| <div class="SRStatus" id="NoMatches">No Matches</div> |
| </div> |
| </div> |
| </div> |
| </div> |
| |
| <div id="nav-path" class="navpath"> |
| <ul> |
| <li class="navelem"><a class="el" href="namespaceiceberg.html">iceberg</a></li><li class="navelem"><a class="el" href="classiceberg_1_1StringUtils.html">StringUtils</a></li> </ul> |
| </div> |
| </div><!-- top --> |
| <div class="header"> |
| <div class="summary"> |
| <a href="#pub-static-methods">Static Public Member Functions</a> | |
| <a href="classiceberg_1_1StringUtils-members.html">List of all members</a> </div> |
| <div class="headertitle"><div class="title">iceberg::StringUtils Class Reference</div></div> |
| </div><!--header--> |
| <div class="contents"> |
| <table class="memberdecls"> |
| <tr class="heading"><td colspan="2"><h2 class="groupheader"><a id="pub-static-methods" name="pub-static-methods"></a> |
| Static Public Member Functions</h2></td></tr> |
| <tr class="memitem:ac1e8069ce9636e1b11ece55292e19a13" id="r_ac1e8069ce9636e1b11ece55292e19a13"><td class="memItemLeft" align="right" valign="top">static std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="classiceberg_1_1StringUtils.html#ac1e8069ce9636e1b11ece55292e19a13">ToLower</a> (std::string_view str)</td></tr> |
| <tr class="memdesc:ac1e8069ce9636e1b11ece55292e19a13"><td class="mdescLeft"> </td><td class="mdescRight">Lower-case a UTF-8 string using Unicode simple (1:1) case mapping. <br /></td></tr> |
| <tr class="separator:ac1e8069ce9636e1b11ece55292e19a13"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a7fe94da00b5c1f2ca831f6a3ee992171" id="r_a7fe94da00b5c1f2ca831f6a3ee992171"><td class="memItemLeft" align="right" valign="top">static std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="classiceberg_1_1StringUtils.html#a7fe94da00b5c1f2ca831f6a3ee992171">ToUpper</a> (std::string_view str)</td></tr> |
| <tr class="memdesc:a7fe94da00b5c1f2ca831f6a3ee992171"><td class="mdescLeft"> </td><td class="mdescRight">Upper-case the ASCII letters (a-z) in a string; all other bytes, including multi-byte UTF-8 sequences, are left unchanged. <br /></td></tr> |
| <tr class="separator:a7fe94da00b5c1f2ca831f6a3ee992171"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:adc967c3db1ca6cd51370b5434d41eec6" id="r_adc967c3db1ca6cd51370b5434d41eec6"><td class="memItemLeft" align="right" valign="top">static bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classiceberg_1_1StringUtils.html#adc967c3db1ca6cd51370b5434d41eec6">EqualsIgnoreCase</a> (std::string_view lhs, std::string_view rhs)</td></tr> |
| <tr class="memdesc:adc967c3db1ca6cd51370b5434d41eec6"><td class="mdescLeft"> </td><td class="mdescRight">Case-insensitive equality using Unicode simple (1:1) case mapping. <br /></td></tr> |
| <tr class="separator:adc967c3db1ca6cd51370b5434d41eec6"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a16467481259b2ce4a426ef7bbd17a8f2" id="r_a16467481259b2ce4a426ef7bbd17a8f2"><td class="memItemLeft" align="right" valign="top">static bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classiceberg_1_1StringUtils.html#a16467481259b2ce4a426ef7bbd17a8f2">StartsWithIgnoreCase</a> (std::string_view str, std::string_view prefix)</td></tr> |
| <tr class="memdesc:a16467481259b2ce4a426ef7bbd17a8f2"><td class="mdescLeft"> </td><td class="mdescRight">Case-insensitive prefix test using Unicode simple (1:1) case mapping. <br /></td></tr> |
| <tr class="separator:a16467481259b2ce4a426ef7bbd17a8f2"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a4a8d82a80d211f1d8b0a33f32810df63" id="r_a4a8d82a80d211f1d8b0a33f32810df63"><td class="memItemLeft" align="right" valign="top"><a id="a4a8d82a80d211f1d8b0a33f32810df63" name="a4a8d82a80d211f1d8b0a33f32810df63"></a> |
| static size_t </td><td class="memItemRight" valign="bottom"><b>CodePointCount</b> (std::string_view str)</td></tr> |
| <tr class="memdesc:a4a8d82a80d211f1d8b0a33f32810df63"><td class="mdescLeft"> </td><td class="mdescRight">Count the number of code points in a UTF-8 string. <br /></td></tr> |
| <tr class="separator:a4a8d82a80d211f1d8b0a33f32810df63"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a1e34eeebde18741afe9ecc29d44a5312" id="r_a1e34eeebde18741afe9ecc29d44a5312"><td class="memTemplParams" colspan="2"><a id="a1e34eeebde18741afe9ecc29d44a5312" name="a1e34eeebde18741afe9ecc29d44a5312"></a> |
| template<typename T > <br /> |
| requires std::is_arithmetic_v<T> && FromChars<T> && (!std::same_as<T, bool>)</td></tr> |
| <tr class="memitem:a1e34eeebde18741afe9ecc29d44a5312"><td class="memTemplItemLeft" align="right" valign="top">static <a class="el" href="namespaceiceberg.html#a9d5594e371beb516b0120e07e69d3af6">Result</a>< T > </td><td class="memTemplItemRight" valign="bottom"><b>ParseNumber</b> (std::string_view str)</td></tr> |
| <tr class="separator:a1e34eeebde18741afe9ecc29d44a5312"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:acc44e09dcfe07b85b8ab96cdb3d1abe0" id="r_acc44e09dcfe07b85b8ab96cdb3d1abe0"><td class="memItemLeft" align="right" valign="top"><a id="acc44e09dcfe07b85b8ab96cdb3d1abe0" name="acc44e09dcfe07b85b8ab96cdb3d1abe0"></a> |
| static <a class="el" href="namespaceiceberg.html#a9d5594e371beb516b0120e07e69d3af6">Result</a>< std::vector< uint8_t > > </td><td class="memItemRight" valign="bottom"><b>HexStringToBytes</b> (std::string_view hex)</td></tr> |
| <tr class="memdesc:acc44e09dcfe07b85b8ab96cdb3d1abe0"><td class="mdescLeft"> </td><td class="mdescRight">Decode a hex string (upper or lower case) into bytes. Returns an error if the string has odd length or contains invalid hex characters. <br /></td></tr> |
| <tr class="separator:acc44e09dcfe07b85b8ab96cdb3d1abe0"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ac58689f5456d78904b64908ecece2aab" id="r_ac58689f5456d78904b64908ecece2aab"><td class="memTemplParams" colspan="2"><a id="ac58689f5456d78904b64908ecece2aab" name="ac58689f5456d78904b64908ecece2aab"></a> |
| template<typename T > <br /> |
| requires std::is_floating_point_v<T> && (!FromChars<T>)</td></tr> |
| <tr class="memitem:ac58689f5456d78904b64908ecece2aab"><td class="memTemplItemLeft" align="right" valign="top">static <a class="el" href="namespaceiceberg.html#a9d5594e371beb516b0120e07e69d3af6">Result</a>< T > </td><td class="memTemplItemRight" valign="bottom"><b>ParseNumber</b> (std::string_view str)</td></tr> |
| <tr class="separator:ac58689f5456d78904b64908ecece2aab"><td class="memSeparator" colspan="2"> </td></tr> |
| </table> |
| <h2 class="groupheader">Member Function Documentation</h2> |
| <a id="adc967c3db1ca6cd51370b5434d41eec6" name="adc967c3db1ca6cd51370b5434d41eec6"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#adc967c3db1ca6cd51370b5434d41eec6">◆ </a></span>EqualsIgnoreCase()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static bool iceberg::StringUtils::EqualsIgnoreCase </td> |
| <td>(</td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>lhs</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>rhs</em> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">inline</span><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Case-insensitive equality using Unicode simple (1:1) case mapping. </p> |
| <p>Equal when the ToLower forms of both operands are equal, so folding follows ToLower's rules (e.g. "İ" (U+0130) folds to "i"). Defined for any byte sequence: ToLower passes invalid UTF-8 bytes through unchanged, so they compare verbatim. </p> |
| |
| </div> |
| </div> |
| <a id="a16467481259b2ce4a426ef7bbd17a8f2" name="a16467481259b2ce4a426ef7bbd17a8f2"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a16467481259b2ce4a426ef7bbd17a8f2">◆ </a></span>StartsWithIgnoreCase()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static bool iceberg::StringUtils::StartsWithIgnoreCase </td> |
| <td>(</td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>str</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>prefix</em> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">inline</span><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Case-insensitive prefix test using Unicode simple (1:1) case mapping. </p> |
| <p><a class="el" href="classiceberg_1_1True.html" title="An Expression that is always true.">True</a> when the ToLower form of str starts with the ToLower form of prefix, so folding follows ToLower's rules (e.g. "İ" (U+0130) folds to "i"). Defined for any byte sequence: ToLower passes invalid UTF-8 bytes through unchanged, so they compare verbatim. </p> |
| |
| </div> |
| </div> |
| <a id="ac1e8069ce9636e1b11ece55292e19a13" name="ac1e8069ce9636e1b11ece55292e19a13"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#ac1e8069ce9636e1b11ece55292e19a13">◆ </a></span>ToLower()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static std::string iceberg::StringUtils::ToLower </td> |
| <td>(</td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>str</em></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Lower-case a UTF-8 string using Unicode simple (1:1) case mapping. </p> |
| <p>Intended for case-insensitive name matching, similar to Iceberg Java's toLowerCase(Locale.ROOT). The mapping is locale-independent, matching the intent of Locale.ROOT. It uses simple (1:1) case mapping rather than Java's full case mapping, so results differ for a few code points; e.g. U+0130 (capital I with dot above) maps to U+0069 ("i") here, but to U+0069 U+0307 ("i" + combining dot above) in Java. For ASCII and the large majority of letters the two agree.</p> |
| <p>Pure-ASCII input takes a byte-wise fast path; utf8proc is only invoked when a non-ASCII byte (>= 0x80) is present. The function is total: it never fails, and input need not be valid UTF-8. A byte that does not begin a valid UTF-8 sequence is copied through unchanged and decoding resumes at the next byte, so the valid code points around it are still lower-cased. See <a href="https://github.com/apache/iceberg-cpp/issues/613">https://github.com/apache/iceberg-cpp/issues/613</a>. </p> |
| |
| </div> |
| </div> |
| <a id="a7fe94da00b5c1f2ca831f6a3ee992171" name="a7fe94da00b5c1f2ca831f6a3ee992171"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a7fe94da00b5c1f2ca831f6a3ee992171">◆ </a></span>ToUpper()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static std::string iceberg::StringUtils::ToUpper </td> |
| <td>(</td> |
| <td class="paramtype">std::string_view </td> |
| <td class="paramname"><em>str</em></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">inline</span><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Upper-case the ASCII letters (a-z) in a string; all other bytes, including multi-byte UTF-8 sequences, are left unchanged. </p> |
| <p>Deliberately ASCII-only and, unlike ToLower, not Unicode-aware. It is only used to normalize ASCII enum/codec strings (e.g. "gzip" -> "GZIP", "all" -> "ALL") for case-insensitive comparison. A Unicode upper-case is intentionally not provided: simple case mapping would be wrong for some letters (e.g. "ß" (U+00DF) would stay unchanged instead of becoming "SS"), and no caller needs it. </p> |
| |
| </div> |
| </div> |
| <hr/>The documentation for this class was generated from the following file:<ul> |
| <li>iceberg/util/<a class="el" href="string__util_8h_source.html">string_util.h</a></li> |
| </ul> |
| </div><!-- contents --> |
| <!-- start footer part --> |
| <hr class="footer"/><address class="footer"><small> |
| Generated by <a href="https://www.doxygen.org/index.html"><img class="footer" src="doxygen.svg" width="104" height="31" alt="doxygen"/></a> 1.9.8 |
| </small></address> |
| </body> |
| </html> |
