From commits-return-101579-archive-asf-public=cust-asf.ponee.io@lucene.apache.org Mon Jun 11 23:16:38 2018 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx-eu-01.ponee.io (Postfix) with SMTP id 11746180789 for ; Mon, 11 Jun 2018 23:16:36 +0200 (CEST) Received: (qmail 88754 invoked by uid 500); 11 Jun 2018 21:16:35 -0000 Mailing-List: contact commits-help@lucene.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@lucene.apache.org Delivered-To: mailing list commits@lucene.apache.org Received: (qmail 88623 invoked by uid 99); 11 Jun 2018 21:16:35 -0000 Received: from git1-us-west.apache.org (HELO git1-us-west.apache.org) (140.211.11.23) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 11 Jun 2018 21:16:35 +0000 Received: by git1-us-west.apache.org (ASF Mail Server at git1-us-west.apache.org, from userid 33) id 2256AE0F99; Mon, 11 Jun 2018 21:16:35 +0000 (UTC) Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: sarowe@apache.org To: commits@lucene.apache.org Date: Mon, 11 Jun 2018 21:16:38 -0000 Message-Id: In-Reply-To: <5673b67a40374c0ea5e5f09730dd3914@git.apache.org> References: <5673b67a40374c0ea5e5f09730dd3914@git.apache.org> X-Mailer: ASF-Git Admin Mailer Subject: [4/6] lucene-solr:branch_7x: LUCENE-8278: Some end-of-input no-scheme domain-only URL tokens are typed as rather than http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/6140d8be/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerImpl.jflex ---------------------------------------------------------------------- diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerImpl.jflex b/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerImpl.jflex index 73a471e..292f2ad 100644 --- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerImpl.jflex +++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerImpl.jflex @@ -83,7 +83,12 @@ ComplexContextEx = \p{LB:Complex_Context} %include ASCIITLD.jflex-macro DomainLabel = [A-Za-z0-9] ([-A-Za-z0-9]* [A-Za-z0-9])? -DomainNameStrict = {DomainLabel} ("." {DomainLabel})* {ASCIITLD} +DomainLabelSequence = {DomainLabel} ("." {DomainLabel})* +DomainNameStrict = {DomainLabelSequence} ({ASCIITLD} | {ASCIITLDprefix_1CharSuffix} | {ASCIITLDprefix_2CharSuffix}) +DomainNameStrict_NoTLDprefix = {DomainLabelSequence} {ASCIITLD} +DomainNameStrict_TLDprefix_1CharSuffix = {DomainLabelSequence} {ASCIITLDprefix_1CharSuffix} +DomainNameStrict_TLDprefix_2CharSuffix = {DomainLabelSequence} {ASCIITLDprefix_2CharSuffix} + DomainNameLoose = {DomainLabel} ("." {DomainLabel})* IPv4DecimalOctet = "0"{0,2} [0-9] | "0"? [1-9][0-9] | "1" [0-9][0-9] | "2" ([0-4][0-9] | "5" [0-5]) @@ -108,7 +113,10 @@ URIlogin = {URIloginSegment} (":" {URIloginSegment})? "@" URIquery = "?" ({URIunreserved} | {URIpercentEncoded} | {URIsubDelims} | [:@/?])* URIfragment = "#" ({URIunreserved} | {URIpercentEncoded} | {URIsubDelims} | [:@/?])* URIport = ":" [0-9]{1,5} -URIhostStrict = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameStrict} +URIhostStrict = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameStrict} +URIhostStrict_NoTLDprefix = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameStrict_NoTLDprefix} +URIhostStrict_TLDprefix_1CharSuffix = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameStrict_TLDprefix_1CharSuffix} +URIhostStrict_TLDprefix_2CharSuffix = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameStrict_TLDprefix_2CharSuffix} URIhostLoose = ("[" {IPv6Address} "]") | {IPv4Address} | {DomainNameLoose} URIauthorityLoose = {URIlogin}? {URIhostLoose} {URIport}? @@ -218,12 +226,16 @@ EMAIL = {EMAILlocalPart} "@" ({DomainNameStrict} | {EMAILbracketedHost}) // Match bad URL (no scheme domain-only URL with a following alphanumeric character) // then change to AVOID_BAD_URL state and pushback the match. -// This rule won't match when in AVOID_BAD_URL state -{URIhostStrict} / [-\w] { yybegin(AVOID_BAD_URL); yypushback(yylength()); } +// These rules won't match when in AVOID_BAD_URL state +// +{URIhostStrict_NoTLDprefix} / [-\w] { yybegin(AVOID_BAD_URL); yypushback(yylength()); } +{URIhostStrict_NoTLDprefix} { return URL_TYPE; } + +{URIhostStrict_TLDprefix_1CharSuffix} / [-\w] { yybegin(AVOID_BAD_URL); yypushback(yylength()); } +{URIhostStrict_TLDprefix_1CharSuffix} { return URL_TYPE; } -// Match a no-schema domain at EOF -// This rule won't match when in AVOID_BAD_URL state -{URIhostStrict} { return URL_TYPE; } +{URIhostStrict_TLDprefix_2CharSuffix} / [-\w] { yybegin(AVOID_BAD_URL); yypushback(yylength()); } +{URIhostStrict_TLDprefix_2CharSuffix} { return URL_TYPE; } { http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/6140d8be/lucene/analysis/common/src/test/org/apache/lucene/analysis/standard/TestUAX29URLEmailTokenizer.java ---------------------------------------------------------------------- diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/standard/TestUAX29URLEmailTokenizer.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/standard/TestUAX29URLEmailTokenizer.java index cfe31c9..f408ee8 100644 --- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/standard/TestUAX29URLEmailTokenizer.java +++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/standard/TestUAX29URLEmailTokenizer.java @@ -557,4 +557,162 @@ public class TestUAX29URLEmailTokenizer extends BaseTokenStreamTestCase { Random random = random(); checkRandomData(random, a, 100*RANDOM_MULTIPLIER, 8192); } + + public void testExampleURLs() throws Exception { + String[] TLDs = { + "aaa", "ac", "ai", "aarp", "abarth", "abb", "abbott", "abbvie", "abc", "able", "abogado", "abudhabi", + "academy", "accenture", "accountant", "accountants", "aco", "active", "actor", "ad", "adac", "ads", "adult", + "ae", "aeg", "aero", "aetna", "af", "afamilycompany", "afl", "africa", "ag", "agakhan", "agency", "aig", + "aigo", "airbus", "airforce", "airtel", "akdn", "al", "alfaromeo", "alibaba", "alipay", "allfinanz", + "allstate", "ally", "alsace", "alstom", "am", "americanexpress", "americanfamily", "amex", "amfam", "amica", + "amsterdam", "analytics", "android", "anquan", "anz", "ao", "aol", "apartments", "app", "apple", "aq", + "aquarelle", "ar", "arab", "aramco", "archi", "army", "arpa", "art", "arte", "as", "asda", "asia", + "associates", "at", "athleta", "attorney", "au", "auction", "audi", "audible", "audio", "auspost", "author", + "auto", "autos", "avianca", "aw", "aws", "ax", "axa", "az", "azure", "ba", "baby", "baidu", "banamex", + "bananarepublic", "band", "bank", "bar", "barcelona", "barclaycard", "barclays", "barefoot", "bargains", + "baseball", "basketball", "bauhaus", "bayern", "bb", "bbc", "bbt", "bbva", "bcg", "bcn", "bd", "be", "beats", + "beauty", "beer", "bentley", "berlin", "best", "bestbuy", "bet", "bf", "bg", "bh", "bharti", "bi", "bible", + "bid", "bike", "bing", "bingo", "bio", "biz", "bj", "black", "blackfriday", "blanco", "blockbuster", "blog", + "bloomberg", "blue", "bm", "bms", "bmw", "bn", "bnl", "bnpparibas", "bo", "boats", "boehringer", "bofa", + "bom", "bond", "boo", "book", "booking", "bosch", "bostik", "boston", "bot", "boutique", "box", "br", + "bradesco", "bridgestone", "broadway", "broker", "brother", "brussels", "bs", "bt", "budapest", "bugatti", + "build", "builders", "business", "buy", "buzz", "bv", "bw", "by", "bz", "bzh", "ca", "cab", "cafe", "cal", + "call", "calvinklein", "cam", "camera", "camp", "cancerresearch", "canon", "capetown", "capital", + "capitalone", "car", "caravan", "cards", "care", "career", "careers", "cars", "cartier", "casa", "case", + "caseih", "cash", "casino", "cat", "catering", "catholic", "cba", "cbn", "cbre", "cbs", "cc", "cd", "ceb", + "center", "ceo", "cern", "cf", "cfa", "cfd", "cg", "ch", "chanel", "channel", "chase", "chat", "cheap", + "chintai", "christmas", "chrome", "chrysler", "church", "ci", "cipriani", "circle", "cisco", "citadel", + "citi", "citic", "city", "cityeats", "ck", "cl", "claims", "cleaning", "click", "clinic", "clinique", + "clothing", "cloud", "club", "clubmed", "cm", "cn", "co", "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", "cr", "credit", "creditcard", "creditunion", "cricket", + "crown", "crs", "cruise", "cruises", "csc", "cu", "cuisinella", "cv", "cw", "cx", "cy", "cymru", "cyou", + "cz", "dabur", "dad", "dance", "data", "date", "dating", "datsun", "day", "dclk", "dds", "de", "deal", + "dealer", "deals", "degree", "delivery", "dell", "deloitte", "delta", "democrat", "dental", "dentist", + "desi", "design", "dev", "dhl", "diamonds", "diet", "digital", "direct", "directory", "discount", "discover", + "dish", "diy", "dj", "dk", "dm", "dnp", "do", "docs", "doctor", "dodge", "dog", "doha", "domains", "dot", + "download", "drive", "dtv", "dubai", "duck", "dunlop", "duns", "dupont", "durban", "dvag", "dvr", "dz", + "earth", "eat", "ec", "eco", "edeka", "edu", "education", "ee", "eg", "email", "emerck", "energy", + "engineer", "engineering", "enterprises", "epost", "epson", "equipment", "er", "ericsson", "erni", "es", + "esq", "estate", "esurance", "et", "etisalat", "eu", "eurovision", "eus", "events", "everbank", "exchange", + "expert", "exposed", "express", "extraspace", "fage", "fail", "fairwinds", "faith", "family", "fan", "fans", + "farm", "farmers", "fashion", "fast", "fedex", "feedback", "ferrari", "ferrero", "fi", "fiat", "fidelity", + "fido", "film", "final", "finance", "financial", "fire", "firestone", "firmdale", "fish", "fishing", "fit", + "fitness", "fj", "fk", "flickr", "flights", "flir", "florist", "flowers", "fly", "fm", "fo", "foo", "food", + "foodnetwork", "football", "ford", "forex", "forsale", "forum", "foundation", "fox", "fr", "free", + "fresenius", "frl", "frogans", "frontdoor", "frontier", "ftr", "fujitsu", "fujixerox", "fun", "fund", + "furniture", "futbol", "fyi", "ga", "gal", "gallery", "gallo", "gallup", "game", "games", "gap", "garden", + "gb", "gbiz", "gd", "gdn", "ge", "gea", "gent", "genting", "george", "gf", "gg", "ggee", "gh", "gi", "gift", + "gifts", "gives", "giving", "gl", "glade", "glass", "gle", "global", "globo", "gm", "gmail", "gmbh", "gmo", + "gmx", "gn", "godaddy", "gold", "goldpoint", "golf", "goo", "goodhands", "goodyear", "goog", "google", "gop", + "got", "gov", "gp", "gq", "gr", "grainger", "graphics", "gratis", "green", "gripe", "grocery", "group", "gs", + "gt", "gu", "guardian", "gucci", "guge", "guide", "guitars", "guru", "gw", "gy", "hair", "hamburg", + "hangout", "haus", "hbo", "hdfc", "hdfcbank", "health", "healthcare", "help", "helsinki", "here", "hermes", + "hgtv", "hiphop", "hisamitsu", "hitachi", "hiv", "hk", "hkt", "hm", "hn", "hockey", "holdings", "holiday", + "homedepot", "homegoods", "homes", "homesense", "honda", "honeywell", "horse", "hospital", "host", "hosting", + "hot", "hoteles", "hotels", "hotmail", "house", "how", "hr", "hsbc", "ht", "hu", "hughes", "hyatt", + "hyundai", "ibm", "icbc", "ice", "icu", "id", "ie", "ieee", "ifm", "ikano", "il", "im", "imamat", "imdb", + "immo", "immobilien", "in", "industries", "infiniti", "info", "ing", "ink", "institute", "insurance", + "insure", "int", "intel", "international", "intuit", "investments", "io", "ipiranga", "iq", "ir", "irish", + "is", "iselect", "ismaili", "ist", "istanbul", "it", "itau", "itv", "iveco", "iwc", "jaguar", "java", "jcb", + "jcp", "je", "jeep", "jetzt", "jewelry", "jio", "jlc", "jll", "jm", "jmp", "jnj", "jo", "jobs", "joburg", + "jot", "joy", "jp", "jpmorgan", "jprs", "juegos", "juniper", "kaufen", "kddi", "ke", "kerryhotels", + "kerrylogistics", "kerryproperties", "kfh", "kg", "kh", "ki", "kia", "kim", "kinder", "kindle", "kitchen", + "kiwi", "km", "kn", "koeln", "komatsu", "kosher", "kp", "kpmg", "kpn", "kr", "krd", "kred", "kuokgroup", + "kw", "ky", "kyoto", "kz", "la", "lacaixa", "ladbrokes", "lamborghini", "lamer", "lancaster", "lancia", + "lancome", "land", "landrover", "lanxess", "lasalle", "lat", "latino", "latrobe", "law", "lawyer", "lb", + "lc", "lds", "lease", "leclerc", "lefrak", "legal", "lego", "lexus", "lgbt", "li", "liaison", "lidl", "life", + "lifeinsurance", "lifestyle", "lighting", "like", "lilly", "limited", "limo", "lincoln", "linde", "link", + "lipsy", "live", "living", "lixil", "lk", "llc", "loan", "loans", "locker", "locus", "loft", "lol", "london", + "lotte", "lotto", "love", "lpl", "lplfinancial", "lr", "ls", "lt", "ltd", "ltda", "lu", "lundbeck", "lupin", + "luxe", "luxury", "lv", "ly", "ma", "macys", "madrid", "maif", "maison", "makeup", "man", "management", + "mango", "map", "market", "marketing", "markets", "marriott", "marshalls", "maserati", "mattel", "mba", "mc", + "mckinsey", "md", "me", "med", "media", "meet", "melbourne", "meme", "memorial", "men", "menu", "merckmsd", + "metlife", "mg", "mh", "miami", "microsoft", "mil", "mini", "mint", "mit", "mitsubishi", "mk", "ml", "mlb", + "mls", "mm", "mma", "mn", "mo", "mobi", "mobile", "mobily", "moda", "moe", "moi", "mom", "monash", "money", + "monster", "mopar", "mormon", "mortgage", "moscow", "moto", "motorcycles", "mov", "movie", "movistar", "mp", + "mq", "mr", "ms", "msd", "mt", "mtn", "mtr", "mu", "museum", "mutual", "mv", "mw", "mx", "my", "mz", "na", + "nab", "nadex", "nagoya", "name", "nationwide", "natura", "navy", "nba", "nc", "ne", "nec", "net", "netbank", + "netflix", "network", "neustar", "new", "newholland", "news", "next", "nextdirect", "nexus", "nf", "nfl", + "ng", "ngo", "nhk", "ni", "nico", "nike", "nikon", "ninja", "nissan", "nissay", "nl", "no", "nokia", + "northwesternmutual", "norton", "now", "nowruz", "nowtv", "np", "nr", "nra", "nrw", "ntt", "nu", "nyc", "nz", + "obi", "observer", "off", "office", "okinawa", "olayan", "olayangroup", "oldnavy", "ollo", "om", "omega", + "one", "ong", "onl", "online", "onyourside", "ooo", "open", "oracle", "orange", "org", "organic", "origins", + "osaka", "otsuka", "ott", "ovh", "pa", "page", "panasonic", "panerai", "paris", "pars", "partners", "parts", + "party", "passagens", "pay", "pccw", "pe", "pet", "pf", "pfizer", "pg", "ph", "pharmacy", "phd", "philips", + "phone", "photo", "photography", "photos", "physio", "piaget", "pics", "pictet", "pictures", "pid", "pin", + "ping", "pink", "pioneer", "pizza", "pk", "pl", "place", "play", "playstation", "plumbing", "plus", "pm", + "pn", "pnc", "pohl", "poker", "politie", "porn", "post", "pr", "pramerica", "praxi", "press", "prime", "pro", + "prod", "productions", "prof", "progressive", "promo", "properties", "property", "protection", "pru", + "prudential", "ps", "pt", "pub", "pw", "pwc", "py", "qa", "qpon", "quebec", "quest", "qvc", "racing", + "radio", "raid", "re", "read", "realestate", "realtor", "realty", "recipes", "red", "redstone", + "redumbrella", "rehab", "reise", "reisen", "reit", "reliance", "ren", "rent", "rentals", "repair", "report", + "republican", "rest", "restaurant", "review", "reviews", "rexroth", "rich", "richardli", "ricoh", + "rightathome", "ril", "rio", "rip", "rmit", "ro", "rocher", "rocks", "rodeo", "rogers", "room", "rs", "rsvp", + "ru", "rugby", "ruhr", "run", "rw", "rwe", "ryukyu", "sa", "saarland", "safe", "safety", "sakura", "sale", + "salon", "samsclub", "samsung", "sandvik", "sandvikcoromant", "sanofi", "sap", "sarl", "sas", "save", "saxo", + "sb", "sbi", "sbs", "sc", "sca", "scb", "schaeffler", "schmidt", "scholarships", "school", "schule", + "schwarz", "science", "scjohnson", "scor", "scot", "sd", "se", "search", "seat", "secure", "security", + "seek", "select", "sener", "services", "ses", "seven", "sew", "sex", "sexy", "sfr", "sg", "sh", "shangrila", + "sharp", "shaw", "shell", "shia", "shiksha", "shoes", "shop", "shopping", "shouji", "show", "showtime", + "shriram", "si", "silk", "sina", "singles", "site", "sj", "sk", "ski", "skin", "sky", "skype", "sl", "sling", + "sm", "smart", "smile", "sn", "sncf", "so", "soccer", "social", "softbank", "software", "sohu", "solar", + "solutions", "song", "sony", "soy", "space", "spiegel", "sport", "spot", "spreadbetting", "sr", "srl", "srt", + "st", "stada", "staples", "star", "starhub", "statebank", "statefarm", "statoil", "stc", "stcgroup", + "stockholm", "storage", "store", "stream", "studio", "study", "style", "su", "sucks", "supplies", "supply", + "support", "surf", "surgery", "suzuki", "sv", "swatch", "swiftcover", "swiss", "sx", "sy", "sydney", + "symantec", "systems", "sz", "tab", "taipei", "talk", "taobao", "target", "tatamotors", "tatar", "tattoo", + "tax", "taxi", "tc", "tci", "td", "tdk", "team", "tech", "technology", "tel", "telecity", "telefonica", + "temasek", "tennis", "teva", "tf", "tg", "th", "thd", "theater", "theatre", "tiaa", "tickets", "tienda", + "tiffany", "tips", "tires", "tirol", "tj", "tjmaxx", "tjx", "tk", "tkmaxx", "tl", "tm", "tmall", "tn", "to", + "today", "tokyo", "tools", "top", "toray", "toshiba", "total", "tours", "town", "toyota", "toys", "tr", + "trade", "trading", "training", "travel", "travelchannel", "travelers", "travelersinsurance", "trust", "trv", + "tt", "tube", "tui", "tunes", "tushu", "tv", "tvs", "tw", "tz", "ua", "ubank", "ubs", "uconnect", "ug", "uk", + "unicom", "university", "uno", "uol", "ups", "us", "uy", "uz", "va", "vacations", "vana", "vanguard", "vc", + "ve", "vegas", "ventures", "verisign", "versicherung", "vet", "vg", "vi", "viajes", "video", "vig", "viking", + "villas", "vin", "vip", "virgin", "visa", "vision", "vista", "vistaprint", "viva", "vivo", "vlaanderen", + "vn", "vodka", "volkswagen", "volvo", "vote", "voting", "voto", "voyage", "vu", "vuelos", "wales", "walmart", + "walter", "wang", "wanggou", "warman", "watch", "watches", "weather", "weatherchannel", "webcam", "weber", + "website", "wed", "wedding", "weibo", "weir", "wf", "whoswho", "wien", "wiki", "williamhill", "win", + "windows", "wine", "winners", "wme", "wolterskluwer", "woodside", "work", "works", "world", "wow", "ws", + "wtc", "wtf", "xbox", "xerox", "xfinity", "xihuan", "xin", "xn--11b4c3d", "xn--1ck2e1b", "xn--1qqw23a", + "xn--2scrj9c", "xn--30rr7y", "xn--3bst00m", "xn--3ds443g", "xn--3e0b707e", "xn--3hcrj9c", + "xn--3oq18vl8pn36a", "xn--3pxu8k", "xn--42c2d9a", "xn--45br5cyl", "xn--45brj9c", "xn--45q11c", "xn--4gbrim", + "xn--54b7fta0cc", "xn--55qw42g", "xn--55qx5d", "xn--5su34j936bgsg", "xn--5tzm5g", "xn--6frz82g", + "xn--6qq986b3xl", "xn--80adxhks", "xn--80ao21a", "xn--80aqecdr1a", "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--gk3at1e", "xn--h2breg3eve", + "xn--h2brj9c", "xn--h2brj9c8c", "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--mgbaakc7dvf", "xn--mgbaam7a8h", "xn--mgbab2bd", + "xn--mgbai9azgqp6j", "xn--mgbayh7gpa", "xn--mgbb9fbpob", "xn--mgbbh1a", "xn--mgbbh1a71e", "xn--mgbc0a9azcg", + "xn--mgbca7dzdo", "xn--mgberp4a5d4ar", "xn--mgbgu82a", "xn--mgbi4ecexp", "xn--mgbpl2fh", "xn--mgbt3dhd", + "xn--mgbtx2b", "xn--mgbx4cd0ab", "xn--mix891f", "xn--mk1bu44c", "xn--mxtq1m", "xn--ngbc5azd", "xn--ngbe9e0a", + "xn--ngbrx", "xn--node", "xn--nqv7f", "xn--nqv7fs00ema", "xn--nyqy26a", "xn--o3cw4h", "xn--ogbpf8fl", + "xn--otu796d", "xn--p1acf", "xn--p1ai", "xn--pbt977c", "xn--pgbs0dh", "xn--pssy2u", "xn--q9jyb4c", + "xn--qcka1pmc", "xn--qxam", "xn--rhqv96g", "xn--rovu88b", "xn--rvc1e0am3e", "xn--s9brj9c", "xn--ses554g", + "xn--t60b56a", "xn--tckwe", "xn--tiq49xqyj", "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", "ye", + "yodobashi", "yoga", "yokohama", "you", "youtube", "yt", "yun", "za", "zappos", "zara", "zero", "zip", + "zippo", "zm", "zone", "zuerich", "zw" + }; + + Analyzer analyzer = new Analyzer() { + @Override protected TokenStreamComponents createComponents(String fieldName) { + return new TokenStreamComponents(new UAX29URLEmailTokenizer(newAttributeFactory())); + }}; + + for (String tld : TLDs) { + String URL = "example." + tld; + BaseTokenStreamTestCase.assertAnalyzesTo(analyzer, URL, new String[]{URL}, new String[]{""}); + } + } } http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/6140d8be/lucene/analysis/common/src/tools/java/org/apache/lucene/analysis/standard/GenerateJflexTLDMacros.java ---------------------------------------------------------------------- diff --git a/lucene/analysis/common/src/tools/java/org/apache/lucene/analysis/standard/GenerateJflexTLDMacros.java b/lucene/analysis/common/src/tools/java/org/apache/lucene/analysis/standard/GenerateJflexTLDMacros.java index 937a4f9..f497938 100644 --- a/lucene/analysis/common/src/tools/java/org/apache/lucene/analysis/standard/GenerateJflexTLDMacros.java +++ b/lucene/analysis/common/src/tools/java/org/apache/lucene/analysis/standard/GenerateJflexTLDMacros.java @@ -20,17 +20,24 @@ import java.io.BufferedReader; import java.io.File; import java.io.FileOutputStream; import java.io.IOException; +import java.io.InputStream; import java.io.InputStreamReader; import java.io.OutputStreamWriter; +import java.io.Reader; import java.io.Writer; import java.net.URL; import java.net.URLConnection; import java.nio.charset.StandardCharsets; import java.text.DateFormat; +import java.util.ArrayList; +import java.util.Comparator; import java.util.Date; +import java.util.List; import java.util.Locale; +import java.util.SortedMap; import java.util.SortedSet; import java.util.TimeZone; +import java.util.TreeMap; import java.util.TreeSet; import java.util.regex.Matcher; import java.util.regex.Pattern; @@ -84,7 +91,10 @@ public class GenerateJflexTLDMacros { private final URL tldFileURL; private long tldFileLastModified = -1L; private final File outputFile; - + private final SortedMap processedTLDsLongestFirst + = new TreeMap<>(Comparator.comparing(String::length).reversed().thenComparing(String::compareTo)); + private final List> TLDsBySuffixLength = new ArrayList<>(); // list position indicates suffix length + public GenerateJflexTLDMacros(String tldFileURL, String outputFile) throws Exception { this.tldFileURL = new URL(tldFileURL); @@ -93,66 +103,101 @@ public class GenerateJflexTLDMacros { /** * Downloads the IANA Root Zone Database, extracts the ASCII TLDs, then - * writes a JFlex macro accepting any of them case-insensitively out to - * the specified output file. + * writes a set of JFlex macros accepting any of them case-insensitively + * out to the specified output file. * * @throws IOException if there is a problem either downloading the database * or writing out the output file. */ public void execute() throws IOException { - final SortedSet TLDs = getIANARootZoneDatabase(); - writeOutput(TLDs); - System.err.println("Wrote " + TLDs.size() + " top level domains to '" - + outputFile + "'."); + getIANARootZoneDatabase(); + partitionTLDprefixesBySuffixLength(); + writeOutput(); + System.out.println("Wrote TLD macros to '" + outputFile + "':"); + int totalDomains = 0; + for (int suffixLength = 0 ; suffixLength < TLDsBySuffixLength.size() ; ++ suffixLength) { + int domainsAtThisSuffixLength = TLDsBySuffixLength.get(suffixLength).size(); + totalDomains += domainsAtThisSuffixLength; + System.out.printf("%30s: %4d TLDs%n", getMacroName(suffixLength), domainsAtThisSuffixLength); + } + System.out.printf("%30s: %4d TLDs%n", "Total", totalDomains); } /** * Downloads the IANA Root Zone Database. - * @return downcased sorted set of ASCII TLDs * @throws java.io.IOException if there is a problem downloading the database */ - private SortedSet getIANARootZoneDatabase() throws IOException { - final SortedSet TLDs = new TreeSet<>(); + private void getIANARootZoneDatabase() throws IOException { final URLConnection connection = tldFileURL.openConnection(); connection.setUseCaches(false); connection.addRequestProperty("Cache-Control", "no-cache"); connection.connect(); tldFileLastModified = connection.getLastModified(); - BufferedReader reader = new BufferedReader - (new InputStreamReader(connection.getInputStream(), StandardCharsets.US_ASCII)); - try { + try (BufferedReader reader = new BufferedReader(new InputStreamReader + (connection.getInputStream(), StandardCharsets.US_ASCII))) { String line; while (null != (line = reader.readLine())) { Matcher matcher = TLD_PATTERN_1.matcher(line); if (matcher.matches()) { - TLDs.add(matcher.group(1).toLowerCase(Locale.ROOT)); + // System.out.println("Found: " + matcher.group(1).toLowerCase(Locale.ROOT)); + processedTLDsLongestFirst.put(matcher.group(1).toLowerCase(Locale.ROOT), Boolean.FALSE); } else { matcher = TLD_PATTERN_2.matcher(line); if (matcher.matches()) { - TLDs.add(matcher.group(1).toLowerCase(Locale.ROOT)); + // System.out.println("Found: " + matcher.group(1).toLowerCase(Locale.ROOT)); + processedTLDsLongestFirst.put(matcher.group(1).toLowerCase(Locale.ROOT), Boolean.FALSE); } } } - } finally { - reader.close(); } - return TLDs; + System.out.println("Found " + processedTLDsLongestFirst.size() + " TLDs in IANA Root Zone Database at " + tldFileURL); } /** + * Partition TLDs by whether they are prefixes of other TLDs and then by suffix length. + * We only care about TLDs that are prefixes and are exactly one character shorter than another TLD. + * See LUCENE-8278 and LUCENE-5391. + */ + private void partitionTLDprefixesBySuffixLength() { + TLDsBySuffixLength.add(new TreeSet<>()); // initialize set for zero-suffix TLDs + for (SortedMap.Entry entry : processedTLDsLongestFirst.entrySet()) { + String TLD = entry.getKey(); + if (entry.getValue()) { + // System.out.println("Skipping already processed: " + TLD); + continue; + } + // System.out.println("Adding zero-suffix TLD: " + TLD); + TLDsBySuffixLength.get(0).add(TLD); + for (int suffixLength = 1 ; (TLD.length() - suffixLength) >= 2 ; ++suffixLength) { + String TLDprefix = TLD.substring(0, TLD.length() - suffixLength); + if (false == processedTLDsLongestFirst.containsKey(TLDprefix)) { + // System.out.println("Ignoring non-TLD prefix: " + TLDprefix); + break; // shorter prefixes can be ignored + } + if (processedTLDsLongestFirst.get(TLDprefix)) { + // System.out.println("Skipping already processed prefix: " + TLDprefix); + break; // shorter prefixes have already been processed + } + + processedTLDsLongestFirst.put(TLDprefix, true); // mark as processed + if (TLDsBySuffixLength.size() == suffixLength) + TLDsBySuffixLength.add(new TreeSet<>()); + SortedSet TLDbucket = TLDsBySuffixLength.get(suffixLength); + TLDbucket.add(TLDprefix); + // System.out.println("Adding TLD prefix of " + TLD + " with suffix length " + suffixLength + ": " + TLDprefix); + } + } + } + + /** * Writes a file containing a JFlex macro that will accept any of the given * TLDs case-insensitively. - * - * @param ASCIITLDs The downcased sorted set of top level domains to accept - * @throws IOException if there is an error writing the output file */ - private void writeOutput(SortedSet ASCIITLDs) throws IOException { + private void writeOutput() throws IOException { final DateFormat dateFormat = DateFormat.getDateTimeInstance - (DateFormat.FULL, DateFormat.FULL, Locale.ROOT); + (DateFormat.FULL, DateFormat.FULL, Locale.ROOT); dateFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - final Writer writer = new OutputStreamWriter - (new FileOutputStream(outputFile), StandardCharsets.UTF_8); - try { + try (Writer writer = new OutputStreamWriter(new FileOutputStream(outputFile), StandardCharsets.UTF_8)) { writer.write(APACHE_LICENSE); writer.write("// Generated from IANA Root Zone Database <"); writer.write(tldFileURL.toString()); @@ -170,26 +215,49 @@ public class GenerateJflexTLDMacros { writer.write(this.getClass().getName()); writer.write(NL); writer.write(NL); - writer.write("ASCIITLD = \".\" ("); - writer.write(NL); - boolean isFirst = true; - for (String ASCIITLD : ASCIITLDs) { - writer.write("\t"); - if (isFirst) { - isFirst = false; - writer.write(" "); + + for (int i = 0; i < TLDsBySuffixLength.size(); ++i) { + String macroName = getMacroName(i); + writer.write("// LUCENE-8278: "); + if (i == 0) { + writer.write("None of the TLDs in {" + macroName + "} is a 1-character-shorter prefix of another TLD"); } else { - writer.write("| "); + writer.write("Each TLD in {" + macroName + "} is a prefix of another TLD by"); + writer.write(" " + i + " character"); + if (i > 1) { + writer.write("s"); + } } - writer.write(getCaseInsensitiveRegex(ASCIITLD)); writer.write(NL); + writeTLDmacro(writer, macroName, TLDsBySuffixLength.get(i)); } - writer.write("\t) \".\"? // Accept trailing root (empty) domain"); - writer.write(NL); + } + } + + private String getMacroName(int suffixLength) { + return "ASCIITLD" + (suffixLength > 0 ? "prefix_" + suffixLength + "CharSuffix" : ""); + } + + private void writeTLDmacro(Writer writer, String macroName, SortedSet TLDs) throws IOException { + writer.write(macroName); + writer.write(" = \".\" ("); + writer.write(NL); + + boolean isFirst = true; + for (String TLD : TLDs) { + writer.write("\t"); + if (isFirst) { + isFirst = false; + writer.write(" "); + } else { + writer.write("| "); + } + writer.write(getCaseInsensitiveRegex(TLD)); writer.write(NL); - } finally { - writer.close(); } + writer.write("\t) \".\"? // Accept trailing root (empty) domain"); + writer.write(NL); + writer.write(NL); } /**