diff --git a/k9mail/src/main/java/com/fsck/k9/message/html/BitcoinUriParser.java b/k9mail/src/main/java/com/fsck/k9/message/html/BitcoinUriParser.java new file mode 100644 index 000000000..f266da7a4 --- /dev/null +++ b/k9mail/src/main/java/com/fsck/k9/message/html/BitcoinUriParser.java @@ -0,0 +1,29 @@ +package com.fsck.k9.message.html; + + +import java.util.regex.Matcher; +import java.util.regex.Pattern; + + +class BitcoinUriParser implements UriParser { + private static final Pattern BITCOIN_URI_PATTERN = + Pattern.compile("bitcoin:[1-9a-km-zA-HJ-NP-Z]{27,34}(\\?[a-zA-Z0-9$\\-_.+!*'(),%:@&=]*)?"); + + @Override + public int linkifyUri(String text, int startPos, StringBuffer outputBuffer) { + Matcher matcher = BITCOIN_URI_PATTERN.matcher(text); + + if (!matcher.find(startPos) || matcher.start() != startPos) { + return startPos; + } + + String bitcoinUri = matcher.group(); + outputBuffer.append("") + .append(bitcoinUri) + .append(""); + + return matcher.end(); + } +} diff --git a/k9mail/src/main/java/com/fsck/k9/message/html/HtmlConverter.java b/k9mail/src/main/java/com/fsck/k9/message/html/HtmlConverter.java index e037c3f1d..9b0e5d9ab 100644 --- a/k9mail/src/main/java/com/fsck/k9/message/html/HtmlConverter.java +++ b/k9mail/src/main/java/com/fsck/k9/message/html/HtmlConverter.java @@ -1,85 +1,30 @@ package com.fsck.k9.message.html; -import android.text.*; -import android.text.Html.TagHandler; -import com.fsck.k9.K9; - -import org.xml.sax.XMLReader; import java.util.Collections; +import java.util.HashMap; import java.util.HashSet; import java.util.Locale; +import java.util.Map; import java.util.Set; import java.util.regex.Matcher; import java.util.regex.Pattern; +import android.text.Annotation; +import android.text.Editable; +import android.text.Html; +import android.text.Html.TagHandler; +import android.text.Spannable; +import android.text.Spanned; +import android.text.TextUtils; + +import com.fsck.k9.K9; +import org.xml.sax.XMLReader; + /** * Contains common routines to convert html to text and vice versa. */ public class HtmlConverter { - /* This comprises most common used Unicode characters allowed in IRI - * as detailed in RFC 3987. - * Specifically, those two byte Unicode characters are not included. - */ - private static final String GOOD_IRI_CHAR = - "a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF"; - /** - * Regular expression to match all IANA top-level domains for WEB_URL. - * List accurate as of 2011/01/12. List taken from: - * http://data.iana.org/TLD/tlds-alpha-by-domain.txt - * This pattern is auto-generated by frameworks/base/common/tools/make-iana-tld-pattern.py - */ - private static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL = - "(?:" - + "(?:aaa|aarp|abarth|abb|abbott|abbvie|abc|able|abogado|abudhabi|academy|accenture|accountant|accountants|aco|active|actor|adac|ads|adult|aeg|aero|aetna|afamilycompany|afl|agakhan|agency|aig|aigo|airbus|airforce|airtel|akdn|alfaromeo|alibaba|alipay|allfinanz|allstate|ally|alsace|alstom|americanexpress|americanfamily|amex|amfam|amica|amsterdam|analytics|android|anquan|anz|apartments|app|apple|aquarelle|aramco|archi|army|arpa|art|arte|asda|asia|associates|athleta|attorney|auction|audi|audible|audio|auspost|author|auto|autos|avianca|aws|axa|azure|a[cdefgilmoqrstuwxz])" - + "|(?:baby|baidu|banamex|bananarepublic|band|bank|bar|barcelona|barclaycard|barclays|barefoot|bargains|bauhaus|bayern|bbc|bbt|bbva|bcg|bcn|beats|beauty|beer|bentley|berlin|best|bestbuy|bet|bharti|bible|bid|bike|bing|bingo|bio|biz|black|blackfriday|blanco|blockbuster|blog|bloomberg|blue|bms|bmw|bnl|bnpparibas|boats|boehringer|bofa|bom|bond|boo|book|booking|boots|bosch|bostik|bot|boutique|bradesco|bridgestone|broadway|broker|brother|brussels|budapest|bugatti|build|builders|business|buy|buzz|bzh|b[abdefghijmnorstvwyz])" - + "|(?:cab|cafe|cal|call|calvinklein|cam|camera|camp|cancerresearch|canon|capetown|capital|capitalone|car|caravan|cards|care|career|careers|cars|cartier|casa|cash|casino|cat|catering|cba|cbn|cbre|cbs|ceb|center|ceo|cern|cfa|cfd|chanel|channel|chase|chat|cheap|chintai|chloe|christmas|chrome|chrysler|church|cipriani|circle|cisco|citadel|citi|citic|city|cityeats|claims|cleaning|click|clinic|clinique|clothing|cloud|club|clubmed|coach|codes|coffee|college|cologne|com|comcast|commbank|community|company|compare|computer|comsec|condos|construction|consulting|contact|contractors|cooking|cookingchannel|cool|coop|corsica|country|coupon|coupons|courses|credit|creditcard|creditunion|cricket|crown|crs|cruises|csc|cuisinella|cymru|cyou|c[acdfghiklmnoruvwxyz])" - + "|(?:dabur|dad|dance|date|dating|datsun|day|dclk|dds|deal|dealer|deals|degree|delivery|dell|deloitte|delta|democrat|dental|dentist|desi|design|dev|dhl|diamonds|diet|digital|direct|directory|discount|discover|dish|diy|dnp|docs|doctor|dodge|dog|doha|domains|dot|download|drive|dtv|dubai|duck|dunlop|duns|dupont|durban|dvag|d[ejkmoz])" - + "|(?:earth|eat|eco|edeka|edu|education|email|emerck|energy|engineer|engineering|enterprises|epost|epson|equipment|ericsson|erni|esq|estate|esurance|eurovision|eus|events|everbank|exchange|expert|exposed|express|extraspace|e[cegrstu])" - + "|(?:fage|fail|fairwinds|faith|family|fan|fans|farm|farmers|fashion|fast|fedex|feedback|ferrari|ferrero|fiat|fidelity|film|final|finance|financial|fire|firestone|firmdale|fish|fishing|fit|fitness|flickr|flights|flir|florist|flowers|fly|foo|foodnetwork|football|ford|forex|forsale|forum|foundation|fox|fresenius|frl|frogans|frontdoor|frontier|ftr|fujitsu|fujixerox|fund|furniture|futbol|fyi|f[ijkmor])" - + "|(?:gal|gallery|gallo|gallup|game|games|gap|garden|gbiz|gdn|gea|gent|genting|george|ggee|gift|gifts|gives|giving|glade|glass|gle|global|globo|gmail|gmbh|gmo|gmx|godaddy|gold|goldpoint|golf|goo|goodhands|goodyear|goog|google|gop|got|gov|grainger|graphics|gratis|green|gripe|group|guardian|gucci|guge|guide|guitars|guru|g[abdefghilmnpqrstuwy])" - + "|(?:hamburg|hangout|haus|hbo|hdfc|hdfcbank|health|healthcare|help|helsinki|here|hermes|hgtv|hiphop|hisamitsu|hitachi|hiv|hkt|hockey|holdings|holiday|homedepot|homegoods|homes|homesense|honda|honeywell|horse|host|hosting|hot|hoteles|hotmail|house|how|hsbc|htc|hughes|hyatt|hyundai|h[kmnrtu])" - + "|(?:ibm|icbc|ice|icu|ieee|ifm|iinet|ikano|imamat|imdb|immo|immobilien|industries|infiniti|info|ing|ink|institute|insurance|insure|int|intel|international|intuit|investments|ipiranga|irish|iselect|ismaili|ist|istanbul|itau|itv|iwc|i[delmnoqrst])" - + "|(?:jaguar|java|jcb|jcp|jeep|jetzt|jewelry|jlc|jll|jmp|jnj|jobs|joburg|jot|joy|jpmorgan|jprs|juegos|juniper|j[emop])" - + "|(?:kaufen|kddi|kerryhotels|kerrylogistics|kerryproperties|kfh|kia|kim|kinder|kindle|kitchen|kiwi|koeln|komatsu|kosher|kpmg|kpn|krd|kred|kuokgroup|kyoto|k[eghimnprwyz])" - + "|(?:lacaixa|ladbrokes|lamborghini|lamer|lancaster|lancia|lancome|land|landrover|lanxess|lasalle|lat|latino|latrobe|law|lawyer|lds|lease|leclerc|lefrak|legal|lego|lexus|lgbt|liaison|lidl|life|lifeinsurance|lifestyle|lighting|like|lilly|limited|limo|lincoln|linde|link|lipsy|live|living|lixil|loan|loans|locker|locus|loft|lol|london|lotte|lotto|love|lpl|lplfinancial|ltd|ltda|lundbeck|lupin|luxe|luxury|l[abcikrstuvy])" - + "|(?:macys|madrid|maif|maison|makeup|man|management|mango|market|marketing|markets|marriott|marshalls|maserati|mattel|mba|mcd|mcdonalds|mckinsey|med|media|meet|melbourne|meme|memorial|men|menu|meo|metlife|miami|microsoft|mil|mini|mint|mit|mitsubishi|mlb|mls|mma|mobi|mobily|moda|moe|moi|mom|monash|money|monster|montblanc|mopar|mormon|mortgage|moscow|motorcycles|mov|movie|movistar|msd|mtn|mtpc|mtr|museum|mutual|mutuelle|m[acdeghklmnopqrstuvwxyz])" - + "|(?:nab|nadex|nagoya|name|nationwide|natura|navy|nba|nec|net|netbank|netflix|network|neustar|new|news|next|nextdirect|nexus|nfl|ngo|nhk|nico|nike|nikon|ninja|nissan|nissay|nokia|northwesternmutual|norton|now|nowruz|nowtv|nra|nrw|ntt|nyc|n[acefgilopruz])" - + "|(?:obi|off|office|okinawa|olayan|olayangroup|oldnavy|ollo|omega|one|ong|onl|online|onyourside|ooo|open|oracle|orange|org|organic|orientexpress|origins|osaka|otsuka|ott|ovh|om)" - + "|(?:page|pamperedchef|panasonic|panerai|paris|pars|partners|parts|party|passagens|pay|pccw|pet|pfizer|pharmacy|philips|photo|photography|photos|physio|piaget|pics|pictet|pictures|pid|pin|ping|pink|pioneer|pizza|place|play|playstation|plumbing|plus|pnc|pohl|poker|politie|porn|post|pramerica|praxi|press|prime|pro|prod|productions|prof|progressive|promo|properties|property|protection|pru|prudential|pub|pwc|p[aefghklmnrstwy])" - + "|(?:qpon|quebec|quest|qvc|qa)" - + "|(?:racing|raid|read|realestate|realtor|realty|recipes|red|redstone|redumbrella|rehab|reise|reisen|reit|ren|rent|rentals|repair|report|republican|rest|restaurant|review|reviews|rexroth|rich|richardli|ricoh|rightathome|rio|rip|rocher|rocks|rodeo|room|rsvp|ruhr|run|rwe|ryukyu|r[eosuw])" - + "|(?:saarland|safe|safety|sakura|sale|salon|samsclub|samsung|sandvik|sandvikcoromant|sanofi|sap|sapo|sarl|sas|save|saxo|sbi|sbs|sca|scb|schaeffler|schmidt|scholarships|school|schule|schwarz|science|scjohnson|scor|scot|seat|secure|security|seek|select|sener|services|ses|seven|sew|sex|sexy|sfr|shangrila|sharp|shaw|shell|shia|shiksha|shoes|shop|shopping|shouji|show|showtime|shriram|silk|sina|singles|site|ski|skin|sky|skype|sling|smart|smile|sncf|soccer|social|softbank|software|sohu|solar|solutions|song|sony|soy|space|spiegel|spot|spreadbetting|srl|srt|stada|staples|star|starhub|statebank|statefarm|statoil|stc|stcgroup|stockholm|storage|store|stream|studio|study|style|sucks|supplies|supply|support|surf|surgery|suzuki|swatch|swiftcover|swiss|sydney|symantec|systems|s[abcdeghijklmnortuvxyz])" - + "|(?:tab|taipei|talk|taobao|target|tatamotors|tatar|tattoo|tax|taxi|tci|tdk|team|tech|technology|tel|telecity|telefonica|temasek|tennis|teva|thd|theater|theatre|tiaa|tickets|tienda|tiffany|tips|tires|tirol|tjmaxx|tjx|tkmaxx|tmall|today|tokyo|tools|top|toray|toshiba|total|tours|town|toyota|toys|trade|trading|training|travel|travelchannel|travelers|travelersinsurance|trust|trv|tube|tui|tunes|tushu|tvs|t[cdfghjklmnortvwz])" - + "|(?:ubank|ubs|uconnect|unicom|university|uno|uol|ups|u[agksyz])" - + "|(?:vacations|vana|vanguard|vegas|ventures|verisign|versicherung|vet|viajes|video|vig|viking|villas|vin|vip|virgin|visa|vision|vista|vistaprint|viva|vivo|vlaanderen|vodka|volkswagen|vote|voting|voto|voyage|vuelos|v[aceginu])" - + "|(?:wales|walmart|walter|wang|wanggou|warman|watch|watches|weather|weatherchannel|webcam|weber|website|wed|wedding|weibo|weir|whoswho|wien|wiki|williamhill|win|windows|wine|winners|wme|wolterskluwer|woodside|work|works|world|wtc|wtf|w[fs])" - + "|(?:xbox|xerox|xfinity|xihuan|xin|xn\\-\\-11b4c3d|xn\\-\\-1ck2e1b|xn\\-\\-1qqw23a|xn\\-\\-30rr7y|xn\\-\\-3bst00m|xn\\-\\-3ds443g|xn\\-\\-3e0b707e|xn\\-\\-3oq18vl8pn36a|xn\\-\\-3pxu8k|xn\\-\\-42c2d9a|xn\\-\\-45brj9c|xn\\-\\-45q11c|xn\\-\\-4gbrim|xn\\-\\-55qw42g|xn\\-\\-55qx5d|xn\\-\\-5su34j936bgsg|xn\\-\\-5tzm5g|xn\\-\\-6frz82g|xn\\-\\-6qq986b3xl|xn\\-\\-80adxhks|xn\\-\\-80ao21a|xn\\-\\-80asehdb|xn\\-\\-80aswg|xn\\-\\-8y0a063a|xn\\-\\-90a3ac|xn\\-\\-90ae|xn\\-\\-90ais|xn\\-\\-9dbq2a|xn\\-\\-9et52u|xn\\-\\-9krt00a|xn\\-\\-b4w605ferd|xn\\-\\-bck1b9a5dre4c|xn\\-\\-c1avg|xn\\-\\-c2br7g|xn\\-\\-cck2b3b|xn\\-\\-cg4bki|xn\\-\\-clchc0ea0b2g2a9gcd|xn\\-\\-czr694b|xn\\-\\-czrs0t|xn\\-\\-czru2d|xn\\-\\-d1acj3b|xn\\-\\-d1alf|xn\\-\\-e1a4c|xn\\-\\-eckvdtc9d|xn\\-\\-efvy88h|xn\\-\\-estv75g|xn\\-\\-fct429k|xn\\-\\-fhbei|xn\\-\\-fiq228c5hs|xn\\-\\-fiq64b|xn\\-\\-fiqs8s|xn\\-\\-fiqz9s|xn\\-\\-fjq720a|xn\\-\\-flw351e|xn\\-\\-fpcrj9c3d|xn\\-\\-fzc2c9e2c|xn\\-\\-fzys8d69uvgm|xn\\-\\-g2xx48c|xn\\-\\-gckr3f0f|xn\\-\\-gecrj9c|xn\\-\\-h2brj9c|xn\\-\\-hxt814e|xn\\-\\-i1b6b1a6a2e|xn\\-\\-imr513n|xn\\-\\-io0a7i|xn\\-\\-j1aef|xn\\-\\-j1amh|xn\\-\\-j6w193g|xn\\-\\-jlq61u9w7b|xn\\-\\-jvr189m|xn\\-\\-kcrx77d1x4a|xn\\-\\-kprw13d|xn\\-\\-kpry57d|xn\\-\\-kpu716f|xn\\-\\-kput3i|xn\\-\\-l1acc|xn\\-\\-lgbbat1ad8j|xn\\-\\-mgb9awbf|xn\\-\\-mgba3a3ejt|xn\\-\\-mgba3a4f16a|xn\\-\\-mgba7c0bbn0a|xn\\-\\-mgbaam7a8h|xn\\-\\-mgbab2bd|xn\\-\\-mgbayh7gpa|xn\\-\\-mgbb9fbpob|xn\\-\\-mgbbh1a71e|xn\\-\\-mgbc0a9azcg|xn\\-\\-mgbca7dzdo|xn\\-\\-mgberp4a5d4ar|xn\\-\\-mgbpl2fh|xn\\-\\-mgbt3dhd|xn\\-\\-mgbtx2b|xn\\-\\-mgbx4cd0ab|xn\\-\\-mix891f|xn\\-\\-mk1bu44c|xn\\-\\-mxtq1m|xn\\-\\-ngbc5azd|xn\\-\\-ngbe9e0a|xn\\-\\-node|xn\\-\\-nqv7f|xn\\-\\-nqv7fs00ema|xn\\-\\-nyqy26a|xn\\-\\-o3cw4h|xn\\-\\-ogbpf8fl|xn\\-\\-p1acf|xn\\-\\-p1ai|xn\\-\\-pbt977c|xn\\-\\-pgbs0dh|xn\\-\\-pssy2u|xn\\-\\-q9jyb4c|xn\\-\\-qcka1pmc|xn\\-\\-qxam|xn\\-\\-rhqv96g|xn\\-\\-rovu88b|xn\\-\\-s9brj9c|xn\\-\\-ses554g|xn\\-\\-t60b56a|xn\\-\\-tckwe|xn\\-\\-unup4y|xn\\-\\-vermgensberater\\-ctb|xn\\-\\-vermgensberatung\\-pwb|xn\\-\\-vhquv|xn\\-\\-vuq861b|xn\\-\\-w4r85el8fhu5dnra|xn\\-\\-w4rs40l|xn\\-\\-wgbh1c|xn\\-\\-wgbl6a|xn\\-\\-xhq521b|xn\\-\\-xkc2al3hye2a|xn\\-\\-xkc2dl3a5ee0h|xn\\-\\-y9a3aq|xn\\-\\-yfro4i67o|xn\\-\\-ygbi2ammx|xn\\-\\-zfr164b|xperia|xxx|xyz)" - + "|(?:yachts|yahoo|yamaxun|yandex|yodobashi|yoga|yokohama|you|youtube|yun|y[et])" - + "|(?:zappos|zara|zero|zip|zippo|zone|zuerich|z[amw])))"; - private static final String BITCOIN_URI_PATTERN = - "bitcoin:[1-9a-km-zA-HJ-NP-Z]{27,34}(\\?[a-zA-Z0-9$\\-_.+!*'(),%:@&=]*)?"; - /** - * Regular expression pattern to match most part of RFC 3987 - * Internationalized URLs, aka IRIs. Commonly used Unicode characters are - * added. - */ - private static final Pattern WEB_URL_PATTERN = Pattern.compile( - "((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)" - + "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_" - + "\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?" - + "((?:(?:[" + GOOD_IRI_CHAR + "][" + GOOD_IRI_CHAR + "\\-]{0,64}\\.)+" // named host - + TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL - + "|(?:(?:25[0-5]|2[0-4]" // or ip address - + "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]" - + "|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]" - + "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}" - + "|[1-9][0-9]|[0-9])))" - + "(?:\\:\\d{1,5})?)" // plus option port number - + "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params - + "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?" - + "(?:\\b|$)"); // and finally, a word boundary or end of - /** * When generating previews, Spannable objects that can't be converted into a String are * represented as 0xfffc. When displayed, these show up as undisplayed squares. These constants @@ -339,7 +284,7 @@ public class HtmlConverter { StringBuffer sb = new StringBuffer(text.length() + TEXT_TO_HTML_EXTRA_BUFFER_LENGTH); sb.append(htmlifyMessageHeader()); - linkifyText(text, sb); + UriLinkifier.linkifyText(text, sb); sb.append(htmlifyMessageFooter()); text = sb.toString(); @@ -428,32 +373,6 @@ public class HtmlConverter { } } - /** - * Searches for link-like text in a string and turn it into a link. Append the result to - * outputBuffer. text is not modified. - * @param text Plain text to be linkified. - * @param outputBuffer Buffer to append linked text to. - */ - protected static void linkifyText(final String text, final StringBuffer outputBuffer) { - String prepared = text.replaceAll(BITCOIN_URI_PATTERN, "$0"); - - Matcher m = WEB_URL_PATTERN.matcher(prepared); - while (m.find()) { - int start = m.start(); - if (start == 0 || (start != 0 && prepared.charAt(start - 1) != '@')) { - if (m.group().indexOf(':') > 0) { // With no URI-schema we may get "http:/" links with the second / missing - m.appendReplacement(outputBuffer, "$0"); - } else { - m.appendReplacement(outputBuffer, "$0"); - } - } else { - m.appendReplacement(outputBuffer, "$0"); - } - } - - m.appendTail(outputBuffer); - } - /* * Lightweight method to check whether the message contains emoji or not. * Useful to avoid calling the heavyweight convertEmoji2Img method. @@ -1384,7 +1303,7 @@ public class HtmlConverter { // Linkify the message. StringBuffer linkified = new StringBuffer(htmlified.length() + TEXT_TO_HTML_EXTRA_BUFFER_LENGTH); - linkifyText(htmlified, linkified); + UriLinkifier.linkifyText(htmlified, linkified); // Add newlines and unescaping. // diff --git a/k9mail/src/main/java/com/fsck/k9/message/html/HttpUriParser.java b/k9mail/src/main/java/com/fsck/k9/message/html/HttpUriParser.java new file mode 100644 index 000000000..1ba302e74 --- /dev/null +++ b/k9mail/src/main/java/com/fsck/k9/message/html/HttpUriParser.java @@ -0,0 +1,302 @@ +package com.fsck.k9.message.html; + + +import java.util.regex.Matcher; +import java.util.regex.Pattern; + + +/** + * Parses and "linkifies" http links. + *

+ * This class is in parts inspired by OkHttp's + * HttpUrl. + * But much of the parsing parts have been left out. + *

+ */ +class HttpUriParser implements UriParser { + // This string represent character group sub-delim as described in RFC 3986 + private static final String SUB_DELIM = "!$&'()*+,;="; + private static final Pattern DOMAIN_PATTERN = + Pattern.compile("[\\da-z](?:[\\da-z-]*[\\da-z])*(?:\\.[\\da-z](?:[\\da-z-]*[\\da-z])*)*(?::(\\d{0,5}))?", + Pattern.CASE_INSENSITIVE); + private static final Pattern IPv4_PATTERN = + Pattern.compile("(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})(:(\\d{0,5}))?"); + + + @Override + public int linkifyUri(String text, int startPos, StringBuffer outputBuffer) { + int currentPos = startPos; + + // Scheme + String shortScheme = text.substring(currentPos, Math.min(currentPos + 7, text.length())); + String longScheme = text.substring(currentPos, Math.min(currentPos + 8, text.length())); + if (shortScheme.equalsIgnoreCase("https://")) { + currentPos += "https://".length(); + } else if (shortScheme.equalsIgnoreCase("http://")) { + currentPos += "http://".length(); + } else if (longScheme.equalsIgnoreCase("rtsp://")) { + currentPos += "rtsp://".length(); + } else { + return startPos; + } + + // Authority + int matchedAuthorityEnd = tryMatchAuthority(text, currentPos); + if (matchedAuthorityEnd == currentPos) { + return startPos; + } + currentPos = matchedAuthorityEnd; + + // Path + if (currentPos < text.length() && text.charAt(currentPos) == '/') { + currentPos = matchUnreservedPCTEncodedSubDelimClassesGreedy(text, currentPos + 1, "/:@"); + } + + // Query + if (currentPos < text.length() && text.charAt(currentPos) == '?') { + currentPos = matchUnreservedPCTEncodedSubDelimClassesGreedy(text, currentPos + 1, ":@/?"); + } + + // Fragment + if (currentPos < text.length() && text.charAt(currentPos) == '#') { + currentPos = matchUnreservedPCTEncodedSubDelimClassesGreedy(text, currentPos + 1, ":@/?"); + } + + String httpUri = text.substring(startPos, currentPos); + outputBuffer.append("") + .append(httpUri) + .append(""); + + return currentPos; + } + + private int tryMatchAuthority(String text, int startPos) { + int authorityLimit = text.indexOf('/', startPos); + if (authorityLimit == -1) { + authorityLimit = text.length(); + } + int authorityStart = tryMatchUserInfo(text, startPos, authorityLimit); + + int authorityEnd = tryMatchDomainName(text, authorityStart); + if (authorityEnd != authorityStart) { + return authorityEnd; + } + + authorityEnd = tryMatchIpv4Address(text, authorityStart, true); + if (authorityEnd != authorityStart) { + return authorityEnd; + } + + authorityEnd = tryMatchIpv6Address(text, authorityStart); + if (authorityEnd != authorityStart) { + return authorityEnd; + } + + return startPos; + } + + private int tryMatchUserInfo(String text, int startPos, int limit) { + int userInfoEnd = text.indexOf('@', startPos); + if (userInfoEnd != -1 && userInfoEnd < limit) { + if (matchUnreservedPCTEncodedSubDelimClassesGreedy(text, startPos, ":") != userInfoEnd) { + // Illegal character in user info + return startPos; + } + return userInfoEnd + 1; + } + return startPos; + } + + private int tryMatchDomainName(String text, int startPos) { + try { + Matcher matcher = DOMAIN_PATTERN.matcher(text); + if (!matcher.find(startPos) || matcher.start() != startPos) { + return startPos; + } + + String portString = matcher.group(1); + if (portString != null && !portString.isEmpty()) { + int port = Integer.parseInt(portString); + if (port > 65535) { + return startPos; + } + } + + return matcher.end(); + } catch (IllegalArgumentException e) { + return startPos; + } + } + + private int tryMatchIpv4Address(String text, int startPos, boolean portAllowed) { + Matcher matcher = IPv4_PATTERN.matcher(text); + if (!matcher.find(startPos) || matcher.start() != startPos) { + return startPos; + } + + for (int i = 1; i <= 4; i++) { + int segment = Integer.parseInt(matcher.group(1)); + if (segment > 255) { + return startPos; + } + } + + if (!portAllowed && matcher.group(5) != null) { + return startPos; + } + + String portString = matcher.group(6); + if (portString != null && !portString.isEmpty()) { + int port = Integer.parseInt(portString); + if (port > 65535) { + return startPos; + } + } + + return matcher.end(); + } + + private int tryMatchIpv6Address(String text, int startPos) { + if (startPos == text.length() || text.codePointAt(startPos) != '[') { + return startPos; + } + + int addressEnd = text.indexOf(']'); + if (addressEnd == -1) { + return startPos; + } + + // Actual parsing + int currentPos = startPos + 1; + int beginSegmentsCount = 0; + int endSegmentsCount = 0; + + // Handle :: separator and segments in front of it + int compressionPos = text.indexOf("::"); + boolean compressionEnabled = compressionPos != -1 && compressionPos < addressEnd; + if (compressionEnabled) { + while (currentPos < compressionPos) { + // Check segment separator + if (beginSegmentsCount > 0) { + if (text.codePointAt(currentPos) != ':') { + return startPos; + } else { + ++currentPos; + } + } + + // Parse segment + int possibleSegmentEnd = + parse16BitHexSegment(text, currentPos, Math.min(currentPos + 4, compressionPos)); + if (possibleSegmentEnd == currentPos) { + return startPos; + } + currentPos = possibleSegmentEnd; + ++beginSegmentsCount; + } + + currentPos += 2; // Skip :: separator + } + + // Parse end segments + while (currentPos < addressEnd && (beginSegmentsCount + endSegmentsCount) < 8) { + // Check segment separator + if (endSegmentsCount > 0) { + if (text.codePointAt(currentPos) != ':') { + return startPos; + } else { + ++currentPos; + } + } + + // Small look ahead, do not run into IPv4 tail (7 is IPv4 minimum length) + int nextColon = text.indexOf(':', currentPos); + if ((nextColon == -1 || nextColon > addressEnd) && (addressEnd - currentPos) >= 7) { + break; + } + + // Parse segment + int possibleSegmentEnd = parse16BitHexSegment(text, currentPos, Math.min(currentPos + 4, addressEnd)); + if (possibleSegmentEnd == currentPos) { + return startPos; + } + currentPos = possibleSegmentEnd; + ++endSegmentsCount; + } + + // We have 3 valid cases here + if (currentPos == addressEnd) { + // 1) No compression and full address, everything fine + // 2) Compression enabled and whole address parsed, everything fine as well + if ((!compressionEnabled && beginSegmentsCount + endSegmentsCount == 8) || + (compressionEnabled && beginSegmentsCount + endSegmentsCount < 8)) { + // Only optional port left, skip address bracket + ++currentPos; + } else { + return startPos; + } + } else { + // 3) Still some stuff missing, check for IPv4 as tail necessary + if (tryMatchIpv4Address(text, currentPos, false) != addressEnd) { + return startPos; + } + currentPos = addressEnd + 1; + } + + // Check optional port + if (currentPos == text.length() || text.codePointAt(currentPos) != ':') { + return currentPos; + } + ++currentPos; + + int port = 0; + for (; currentPos < text.length(); currentPos++) { + int c = text.codePointAt(currentPos); + if (c < '0' || c > '9') { + break; + } + port = port * 10 + c - '0'; + } + return (port <= 65535) ? currentPos : startPos; + } + + private int parse16BitHexSegment(String text, int startPos, int endPos) { + int currentPos = startPos; + while (isHexDigit(text.codePointAt(currentPos)) && currentPos < endPos) { + ++currentPos; + } + + return currentPos; + } + + private int matchUnreservedPCTEncodedSubDelimClassesGreedy(String text, int startPos, String additionalCharacters) { + String allowedCharacters = SUB_DELIM + "-._~" + additionalCharacters; + int currentPos; + int shouldBeHex = 0; + for (currentPos = startPos; currentPos < text.length(); currentPos++) { + int c = text.codePointAt(currentPos); + + if (isHexDigit(c)) { + shouldBeHex = Math.max(shouldBeHex - 1, 0); + } else if (shouldBeHex == 0) { + if (allowedCharacters.indexOf(c) != -1) { + // Everything ok here :) + } else if (c == '%') { + shouldBeHex = 2; + } else { + break; + } + } else { + break; + } + } + + return currentPos; + } + + private boolean isHexDigit(int c) { + return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9'); + } +} diff --git a/k9mail/src/main/java/com/fsck/k9/message/html/UriLinkifier.java b/k9mail/src/main/java/com/fsck/k9/message/html/UriLinkifier.java new file mode 100644 index 000000000..01ee239e6 --- /dev/null +++ b/k9mail/src/main/java/com/fsck/k9/message/html/UriLinkifier.java @@ -0,0 +1,63 @@ +package com.fsck.k9.message.html; + + +import java.util.HashMap; +import java.util.Locale; +import java.util.Map; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +import android.text.TextUtils; + + +public class UriLinkifier { + private static final Pattern URI_SCHEME; + private static final Map SUPPORTED_URIS; + private static final String SCHEME_SEPARATORS = " (\\n"; + private static final String ALLOWED_SEPARATORS_PATTERN = "(?:^|[" + SCHEME_SEPARATORS + "])"; + + static { + SUPPORTED_URIS = new HashMap<>(); + SUPPORTED_URIS.put("bitcoin:", new BitcoinUriParser()); + UriParser httpParser = new HttpUriParser(); + SUPPORTED_URIS.put("http:", httpParser); + SUPPORTED_URIS.put("https:", httpParser); + SUPPORTED_URIS.put("rtsp:", httpParser); + + String allSchemes = TextUtils.join("|", SUPPORTED_URIS.keySet()); + String pattern = ALLOWED_SEPARATORS_PATTERN + "(" + allSchemes + ")"; + URI_SCHEME = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE); + } + + + public static void linkifyText(String text, StringBuffer outputBuffer) { + int currentPos = 0; + Matcher matcher = URI_SCHEME.matcher(text); + + while (matcher.find(currentPos)) { + int startPos = matcher.start(1); + + String textBeforeMatch = text.substring(currentPos, startPos); + outputBuffer.append(textBeforeMatch); + + String scheme = matcher.group(1).toLowerCase(Locale.US); + UriParser parser = SUPPORTED_URIS.get(scheme); + int newPos = parser.linkifyUri(text, startPos, outputBuffer); + + boolean uriWasNotLinkified = newPos <= startPos; + if (uriWasNotLinkified) { + outputBuffer.append(text.charAt(startPos)); + currentPos = startPos + 1; + } else { + currentPos = (newPos > currentPos) ? newPos : currentPos + 1; + } + + if (currentPos >= text.length()) { + break; + } + } + + String textAfterLastMatch = text.substring(currentPos); + outputBuffer.append(textAfterLastMatch); + } +} diff --git a/k9mail/src/main/java/com/fsck/k9/message/html/UriParser.java b/k9mail/src/main/java/com/fsck/k9/message/html/UriParser.java new file mode 100644 index 000000000..ad08c0d14 --- /dev/null +++ b/k9mail/src/main/java/com/fsck/k9/message/html/UriParser.java @@ -0,0 +1,19 @@ +package com.fsck.k9.message.html; + + +public interface UriParser { + /** + * Parse and linkify scheme specific URI beginning from given position. The result will be written to given buffer. + * + * @param text + * String to parse URI from. + * @param startPos + * Position where URI starts (first letter of scheme). + * @param outputBuffer + * Buffer where linkified variant of URI is written to. + * + * @return Index where parsed URI ends (first non-URI letter). Should be {@code startPos} or smaller if no valid + * URI was found. + */ + int linkifyUri(String text, int startPos, StringBuffer outputBuffer); +} diff --git a/k9mail/src/test/java/com/fsck/k9/message/html/BitcoinUriParserTest.java b/k9mail/src/test/java/com/fsck/k9/message/html/BitcoinUriParserTest.java new file mode 100644 index 000000000..12b9f5bbf --- /dev/null +++ b/k9mail/src/test/java/com/fsck/k9/message/html/BitcoinUriParserTest.java @@ -0,0 +1,84 @@ +package com.fsck.k9.message.html; + + +import org.junit.Test; + +import static com.fsck.k9.message.html.UriParserTestHelper.assertLinkOnly; +import static org.junit.Assert.assertEquals; + + +public class BitcoinUriParserTest { + BitcoinUriParser parser = new BitcoinUriParser(); + StringBuffer outputBuffer = new StringBuffer(); + + + @Test + public void basicBitcoinUri() throws Exception { + assertLinkify("bitcoin:19W6QZkx8SYPG7BBCS7odmWGRxqRph5jFU"); + } + + @Test + public void bitcoinUriWithAmount() throws Exception { + assertLinkify("bitcoin:12A1MyfXbW6RhdRAZEqofac5jCQQjwEPBu?amount=1.2"); + } + + @Test + public void bitcoinUriWithQueryParameters() throws Exception { + assertLinkify("bitcoin:12A1MyfXbW6RhdRAZEqofac5jCQQjwEPBu?amount=1.2" + + "&message=Payment&label=Satoshi&extra=other-param"); + } + + @Test + public void uriInMiddleOfInput() throws Exception { + String prefix = "prefix "; + String uri = "bitcoin:12A1MyfXbW6RhdRAZEqofac5jCQQjwEPBu?amount=1.2"; + String text = prefix + uri; + + parser.linkifyUri(text, prefix.length(), outputBuffer); + + assertLinkOnly(uri, outputBuffer); + } + + @Test + public void invalidScheme() throws Exception { + assertNotLinkify("bitcion:19W6QZkx8SYPG7BBCS7odmWGRxqRph5jFU"); + } + + @Test + public void invalidAddress() throws Exception { + assertNotLinkify("bitcoin:[invalid]"); + } + + @Test + public void invalidBitcoinUri_shouldReturnStartingPosition() throws Exception { + String uri = "bitcoin:[invalid]"; + + int newPos = linkify(uri); + + assertEquals(0, newPos); + } + + @Test + public void invalidBitcoinUri_shouldNotWriteToOutputBuffer() throws Exception { + String uri = "bitcoin:[invalid]"; + + linkify(uri); + + assertEquals(0, outputBuffer.length()); + } + + + int linkify(String uri) { + return parser.linkifyUri(uri, 0, outputBuffer); + } + + void assertLinkify(String uri) { + linkify(uri); + assertLinkOnly(uri, outputBuffer); + } + + void assertNotLinkify(String text) { + int newPos = linkify(text); + assertEquals(0, newPos); + } +} diff --git a/k9mail/src/test/java/com/fsck/k9/message/html/HtmlConverterTest.java b/k9mail/src/test/java/com/fsck/k9/message/html/HtmlConverterTest.java index 28ce3cf3f..9cd79b53d 100644 --- a/k9mail/src/test/java/com/fsck/k9/message/html/HtmlConverterTest.java +++ b/k9mail/src/test/java/com/fsck/k9/message/html/HtmlConverterTest.java @@ -193,21 +193,6 @@ public class HtmlConverterTest { + "", result); } - @Test - public void testLinkifyBitcoinAndHttpUri() { - String text = "bitcoin:19W6QZkx8SYPG7BBCS7odmWGRxqRph5jFU http://example.com/"; - - StringBuffer outputBuffer = new StringBuffer(); - HtmlConverter.linkifyText(text, outputBuffer); - - assertEquals("" + - "bitcoin:19W6QZkx8SYPG7BBCS7odmWGRxqRph5jFU" + - " " + - "" + - "http://example.com/" + - "", outputBuffer.toString()); - } - @Test public void issue2259Spec() { String text = "text\n" + diff --git a/k9mail/src/test/java/com/fsck/k9/message/html/HttpUriParserTest.java b/k9mail/src/test/java/com/fsck/k9/message/html/HttpUriParserTest.java new file mode 100644 index 000000000..1e9ae8906 --- /dev/null +++ b/k9mail/src/test/java/com/fsck/k9/message/html/HttpUriParserTest.java @@ -0,0 +1,209 @@ +package com.fsck.k9.message.html; + + +import org.junit.Test; + +import static com.fsck.k9.message.html.UriParserTestHelper.assertLinkOnly; +import static junit.framework.Assert.assertEquals; + + +public class HttpUriParserTest { + private final HttpUriParser parser = new HttpUriParser(); + private final StringBuffer outputBuffer = new StringBuffer(); + + + @Test + public void emptyUriIgnored() { + assertLinkIgnored("http://"); + } + + @Test + public void emptyAuthorityIgnored() { + assertLinkIgnored("http:///"); + } + + @Test + public void simpleDomain() { + assertLinkify("http://www.google.com"); + } + + @Test + public void invalidDomainIgnored() { + assertLinkIgnored("http://-www.google.com"); + } + + @Test + public void domainWithTrailingSlash() { + assertLinkify("http://www.google.com/"); + } + + @Test + public void domainWithUserInfo() { + assertLinkify("http://test@google.com/"); + } + + @Test + public void domainWithFullUserInfo() { + assertLinkify("http://test:secret@google.com/"); + } + + @Test + public void domainWithoutWww() { + assertLinkify("http://google.com/"); + } + + @Test + public void query() { + assertLinkify("http://google.com/give/me/?q=mode&c=information"); + } + + @Test + public void fragment() { + assertLinkify("http://google.com/give/me#only-the-best"); + } + + @Test + public void queryAndFragment() { + assertLinkify("http://google.com/give/me/?q=mode&c=information#only-the-best"); + } + + @Test + public void ipv4Address() { + assertLinkify("http://127.0.0.1"); + } + + @Test + public void ipv4AddressWithTrailingSlash() { + assertLinkify("http://127.0.0.1/"); + } + + @Test + public void ipv4AddressWithEmptyPort() { + assertLinkify("http://127.0.0.1:"); + } + + @Test + public void ipv4AddressWithPort() { + assertLinkify("http://127.0.0.1:524/"); + } + + @Test + public void ipv6Address() { + assertLinkify("http://[FEDC:BA98:7654:3210:FEDC:BA98:7654:3210]"); + } + + @Test + public void ipv6AddressWithPort() { + assertLinkify("http://[FEDC:BA98:7654:3210:FEDC:BA98:7654:3210]:80"); + } + + @Test + public void ipv6AddressWithTrailingSlash() { + assertLinkify("http://[1080:0:0:0:8:800:200C:417A]/"); + } + + @Test + public void ipv6AddressWithEndCompression() { + assertLinkify("http://[3ffe:2a00:100:7031::1]"); + } + + @Test + public void ipv6AddressWithBeginCompression() { + assertLinkify("http://[1080::8:800:200C:417A]/"); + } + + @Test + public void ipv6AddressWithCompressionPort() { + assertLinkify("http://[::FFFF:129.144.52.38]:80/"); + } + + @Test + public void ipv6AddressWithPrependedCompression() { + assertLinkify("http://[::192.9.5.5]/"); + } + + @Test + public void ipv6AddressWithTrailingIp4AndPort() { + assertLinkify("http://[::192.9.5.5]:80/"); + } + + @Test + public void ipv6WithoutClosingSquareBracketIgnored() { + assertLinkIgnored("http://[1080:0:0:0:8:80:200C:417A/"); + } + + @Test + public void ipv6InvalidClosingSquareBracketIgnored() { + assertLinkIgnored("http://[1080:0:0:0:8:800:270C:417A/]"); + } + + @Test + public void domainWithTrailingSpace() { + String text = "http://google.com/ "; + + int endPos = parser.linkifyUri(text, 0, outputBuffer); + + assertLinkOnly("http://google.com/", outputBuffer); + assertEquals(text.length() - 1, endPos); + } + + @Test + public void domainWithTrailingNewline() { + String text = "http://google.com/\n"; + + int endPos = parser.linkifyUri(text, 0, outputBuffer); + + assertLinkOnly("http://google.com/", outputBuffer); + assertEquals(text.length() - 1, endPos); + } + + @Test + public void domainWithTrailingAngleBracket() { + String text = ""; + + int endPos = parser.linkifyUri(text, 1, outputBuffer); + + assertLinkOnly("http://google.com/", outputBuffer); + assertEquals(text.length() - 1, endPos); + } + + @Test + public void uriInMiddleAfterInput() { + String prefix = "prefix "; + String uri = "http://google.com/"; + String text = prefix + uri; + + parser.linkifyUri(text, prefix.length(), outputBuffer); + + assertLinkOnly(uri, outputBuffer); + } + + @Test + public void uriInMiddleOfInput() { + String prefix = "prefix "; + String uri = "http://google.com/"; + String postfix = " postfix"; + String text = prefix + uri + postfix; + + parser.linkifyUri(text, prefix.length(), outputBuffer); + + assertLinkOnly(uri, outputBuffer); + } + + + int linkify(String uri) { + return parser.linkifyUri(uri, 0, outputBuffer); + } + + void assertLinkify(String uri) { + linkify(uri); + assertLinkOnly(uri, outputBuffer); + } + + void assertLinkIgnored(String uri) { + int endPos = linkify(uri); + + assertEquals("", outputBuffer.toString()); + assertEquals(0, endPos); + } +} diff --git a/k9mail/src/test/java/com/fsck/k9/message/html/UriLinkifierTest.java b/k9mail/src/test/java/com/fsck/k9/message/html/UriLinkifierTest.java new file mode 100644 index 000000000..3b02dc035 --- /dev/null +++ b/k9mail/src/test/java/com/fsck/k9/message/html/UriLinkifierTest.java @@ -0,0 +1,139 @@ +package com.fsck.k9.message.html; + + +import com.fsck.k9.K9RobolectricTestRunner; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.robolectric.annotation.Config; + +import static com.fsck.k9.message.html.UriParserTestHelper.assertLinkOnly; +import static junit.framework.Assert.assertEquals; + + +@RunWith(K9RobolectricTestRunner.class) +@Config(manifest = Config.NONE) +public class UriLinkifierTest { + private StringBuffer outputBuffer = new StringBuffer(); + + + @Test + public void emptyText() { + String text = ""; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals(text, outputBuffer.toString()); + } + + @Test + public void textWithoutUri_shouldBeCopiedToOutputBuffer() { + String text = "some text here"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals(text, outputBuffer.toString()); + } + + @Test + public void simpleUri() { + String uri = "http://example.org"; + + UriLinkifier.linkifyText(uri, outputBuffer); + + assertLinkOnly(uri, outputBuffer); + } + + @Test + public void uriPrecededBySpace() { + String text = " http://example.org"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals(" http://example.org", outputBuffer.toString()); + } + + @Test + public void uriPrecededByOpeningParenthesis() { + String text = "(http://example.org"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals("(http://example.org", outputBuffer.toString()); + } + + @Test + public void uriPrecededBySomeText() { + String uri = "Check out my fantastic URI: http://example.org"; + + UriLinkifier.linkifyText(uri, outputBuffer); + + assertEquals("Check out my fantastic URI: http://example.org", + outputBuffer.toString()); + } + + @Test + public void uriWithTrailingText() { + String uri = "http://example.org/ is the best"; + + UriLinkifier.linkifyText(uri, outputBuffer); + + assertEquals("http://example.org/ is the best", outputBuffer.toString()); + } + + @Test + public void uriEmbeddedInText() { + String uri = "prefix http://example.org/ suffix"; + + UriLinkifier.linkifyText(uri, outputBuffer); + + assertEquals("prefix http://example.org/ suffix", outputBuffer.toString()); + } + + @Test + public void uriWithUppercaseScheme() { + String uri = "HTTP://example.org/"; + + UriLinkifier.linkifyText(uri, outputBuffer); + + assertEquals("HTTP://example.org/", outputBuffer.toString()); + } + + @Test + public void uriNotPrecededByValidSeparator_shouldNotBeLinkified() { + String text = "myhttp://example.org"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals(text, outputBuffer.toString()); + } + + @Test + public void uriNotPrecededByValidSeparatorFollowedByValidUri() { + String text = "myhttp: http://example.org"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals("myhttp: http://example.org", outputBuffer.toString()); + } + + @Test + public void schemaMatchWithInvalidUriInMiddleOfTextFollowedByValidUri() { + String text = "prefix http:42 http://example.org"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals("prefix http:42 http://example.org", outputBuffer.toString()); + } + + @Test + public void multipleValidUrisInRow() { + String text = "prefix http://uri1.example.org some text http://uri2.example.org/path postfix"; + + UriLinkifier.linkifyText(text, outputBuffer); + + assertEquals( + "prefix http://uri1.example.org some text " + + "http://uri2.example.org/path postfix", + outputBuffer.toString()); + } +} diff --git a/k9mail/src/test/java/com/fsck/k9/message/html/UriParserTestHelper.java b/k9mail/src/test/java/com/fsck/k9/message/html/UriParserTestHelper.java new file mode 100644 index 000000000..a57ea4b48 --- /dev/null +++ b/k9mail/src/test/java/com/fsck/k9/message/html/UriParserTestHelper.java @@ -0,0 +1,38 @@ +package com.fsck.k9.message.html; + + +import org.jsoup.Jsoup; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; + +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertNotNull; +import static org.junit.Assert.assertTrue; + + +public class UriParserTestHelper { + public static void assertContainsLink(String expected, StringBuffer actual) { + String linkifiedUri = actual.toString(); + Document document = Jsoup.parseBodyFragment(linkifiedUri); + Element anchorElement = document.select("a").first(); + assertNotNull("No element found", anchorElement); + assertEquals(expected, anchorElement.text()); + assertEquals(expected, anchorElement.attr("href")); + } + + public static void assertLinkOnly(String expected, StringBuffer actual) { + String linkifiedUri = actual.toString(); + Document document = Jsoup.parseBodyFragment(linkifiedUri); + Element anchorElement = document.select("a").first(); + assertNotNull("No element found", anchorElement); + assertEquals(expected, anchorElement.text()); + assertEquals(expected, anchorElement.attr("href")); + + assertAnchorElementIsSoleContent(document, anchorElement); + } + + private static void assertAnchorElementIsSoleContent(Document document, Element anchorElement) { + assertEquals(document.body(), anchorElement.parent()); + assertTrue(" element is surrounded by text", document.body().textNodes().isEmpty()); + } +}