R中的unicode字符转换_R_Unicode

R中的unicode字符转换

r unicode

R中的unicode字符转换,r,unicode,R,Unicode,我有这个MTST列，当打印出来时 [1] "<U+0391>G<U+03A1><U+0399><U+039D><U+0399><U+039F> " [2] "<U+0391>G<U+03A7><U+0399><U+0391><U+039B><U+039F>S

我有这个

MTST

列，当打印出来时

 [1] "<U+0391>G<U+03A1><U+0399><U+039D><U+0399><U+039F>                                 "
 [2] "<U+0391>G<U+03A7><U+0399><U+0391><U+039B><U+039F>S                                "
 [3] "<U+0391><U+0399>G<U+0399><U+039D><U+0391>                                  "
 [4] "<U+0391><U+0399>G<U+0399><U+039F>                                   "
 [5] "<U+0391><U+0399><U+0394><U+0397><U+03A8><U+039F>S                                 "
 [6] "<U+0391><U+039A><U+03A4><U+0399><U+039F>(<U+03A0><U+03A1><U+0395><U+0392><U+0395><U+0396><U+0391>)                          "
 [7] "<U+0391><U+039B><U+0395><U+039E><U+0391><U+039D><U+0394><U+03A1><U+039F><U+03A5><U+03A0><U+039F><U+039B><U+0397>                          "
 [8] "<U+0391><U+039B><U+0399><U+0391><U+03A1><U+03A4><U+039F>S                                "

我也尝试了

dump

和

dput

，但没有任何改变

请注意，

MTST

最初的类型是

字符

谢谢你的帮助。谢谢

编辑：显示以下
dput（MTST）

c("<U+0391>G<U+03A1><U+0399><U+039D><U+0399><U+039F> ", "<U+0391>G<U+03A7><U+0399><U+0391><U+039B><U+039F>S ", "<U+0391><U+0399>G<U+0399><U+039D><U+0391> ", "<U+0391><U+0399>G<U+0399><U+039F> ", "<U+0391><U+0399><U+0394><U+0397><U+03A8><U+039F>S ", "<U+0391><U+039A><U+03A4><U+0399><U+039F>(<U+03A0><U+03A1><U+0395><U+0392><U+0395><U+0396><U+0391>) ", "<U+0391><U+039B><U+0395><U+039E><U+0391><U+039D><U+0394><U+03A1><U+039F><U+03A5><U+03A0><U+039F><U+039B><U+0397> ", "<U+0391><U+039B><U+0399><U+0391><U+03A1><U+03A4><U+039F>S ", "<U+0391><U+039D><U+0391><U+0392><U+03A1><U+03A5><U+03A4><U+0391> ", "<U+0391><U+039D><U+0394><U+03A1><U+0391><U+0392><U+0399><U+0394><U+0391> ", "<U+0391><U+039D>OG<U+0395><U+0399><U+0391> ", "<U+0391><U+03A1><U+0391><U+039E><U+039F>S ", "<U+0391><U+03A1><U+0391><U+03A7>O<U+0392><U+0391> ", "<U+0391><U+03A1>G<U+039F>S(<U+03A0><U+03A5><U+03A1>G<U+0395><U+039B><U+0391>) ", "<U+0391><U+03A1>G<U+039F>S<U+03A4><U+039F><U+039B><U+0399> ", "<U+0391><U+03A1><U+03A4><U+0391> (<U+03A0><U+039F><U+039B><U+0397>) ", "<U+0391><U+03A1><U+03A4><U+0391> (F<U+0399><U+039B><U+039F>T<U+0395><U+0397>) ", "<U+0391>S<U+03A4><U+0395><U+03A1><U+039F>S<U+039A><U+039F><U+03A0><U+0395><U+0399><U+039F> ", "<U+0391>S<U+03A4><U+03A1><U+039F>S ", "<U+0391>S<U+03A4><U+03A5><U+03A0><U+0391><U+039B><U+0391><U+0399><U+0391> ", "<U+0392><U+0391><U+039C><U+039F>S ", "<U+0392><U+0395><U+039B><U+039F> (<U+039A><U+039F><U+03A1><U+0399><U+039D>T<U+0399><U+0391>S) ", "<U+0392><U+039F><U+039B><U+039F>S ", "<U+0392><U+03A5><U+03A4><U+0399><U+039D><U+0391> ", "G<U+039F><U+03A1><U+03A4><U+03A5>S ", "G<U+03A5>T<U+0395><U+0399><U+039F> ", "<U+0394><U+0395>SF<U+0399><U+039D><U+0391> ", "<U+0394><U+0399><U+0391><U+0392><U+039F><U+039B><U+0399><U+03A4>S<U+0399> ", "<U+0394><U+039F><U+039C><U+039F><U+039A><U+039F>S ", "<U+0394><U+03A1><U+0391><U+039C><U+0391> ", "<U+0395><U+0394><U+0395>SS<U+0391> ", "<U+0395><U+039B><U+0395><U+03A5>S<U+0399><U+039D><U+0391> ", "<U+0395><U+039B><U+039B><U+0397><U+039D><U+0399><U+039A><U+039F> ae<U+03C1> ", "<U+0396><U+0391><U+039A><U+03A5><U+039D>T<U+039F>S ", "<U+0396><U+0391><U+039A><U+03A5><U+039D>T<U+039F>S_<U+03A0><U+039F><U+039B><U+0397> ", "<U+0396><U+0391><U+03A1><U+039F>S ", "<U+0397><U+03A1><U+0391><U+039A><U+039B><U+0395><U+0399><U+039F> ", "T<U+0391>S<U+039F>S ", "T<U+0397><U+03A1><U+0391> (S<U+0391><U+039D><U+03A4><U+039F><U+03A1><U+0399><U+039D><U+0397>", "<U+0399><U+0395><U+03A1><U+0391><U+03A0><U+0395><U+03A4><U+03A1><U+0391> ", "<U+0399><U+039A><U+0391><U+03A1><U+0399><U+0391>_<U+0391>/<U+0394> ", "<U+0399>O<U+0391><U+039D><U+039D><U+0399><U+039D><U+0391> ", "<U+039A><U+0391><U+0392><U+0391><U+039B><U+0391> (<U+03A0><U+039F><U+039B><U+0397>) ", "<U+039A><U+0391><U+0392><U+0391><U+039B><U+0391>(<U+0391><U+039C><U+03A5>G<U+0394><U+0391><U+039B><U+0395>O<U+039D><U+0391>S) ", "<U+039A><U+0391><U+039B><U+0391><U+0392><U+03A1><U+03A5><U+03A4><U+0391> ", "<U+039A><U+0391><U+039B><U+0391><U+039C><U+0391><U+03A4><U+0391> ", "<U+039A><U+0391><U+039B><U+0391><U+039C><U+03A0><U+0391><U+039A><U+0391> ", "<U+039A><U+0391><U+03A1><U+0394><U+0399><U+03A4>S<U+0391> ", "<U+039A><U+0391><U+03A1><U+03A0><U+0391>T<U+039F>S_<U+0391>/<U+0394> ", "<U+039A><U+0391><U+03A1><U+03A0><U+0391>T<U+039F>S_<U+03A0><U+039F><U+039B><U+0397> ", "<U+039A><U+0391><U+03A1><U+03A0><U+0395><U+039D><U+0397>S<U+0399> ", "<U+039A><U+0391><U+03A1><U+03A5>S<U+03A4><U+039F>S ", "<U+039A><U+0391>S<U+039F>S ", "<U+039A><U+0391>S<U+03A4><U+0395><U+039B><U+039B><U+0399> ", "<U+039A><U+0391>S<U+03A4><U+039F><U+03A1><U+0399><U+0391> ", "<U+039A><U+0395><U+03A1><U+039A><U+03A5><U+03A1><U+0391> ", "<U+039A><U+039F><U+0396><U+0391><U+039D><U+0397> ", "<U+039A><U+039F><U+039C><U+039F><U+03A4><U+0397><U+039D><U+0397> ", "<U+039A><U+039F><U+039D><U+0399><U+03A4>S<U+0391> ", "<U+039A><U+039F><U+03A1><U+0399><U+039D>T<U+039F>S ", "<U+039A><U+03A5>T<U+0397><U+03A1><U+0391>_<U+0391>/<U+0394> ", "<U+039A><U+03A5><U+039C><U+0397> ", "<U+039A>OS ", "<U+039A>OS_<U+03A0><U+039F><U+039B><U+0397> ", "<U+039B><U+0391><U+039C><U+0399><U+0391> ", "<U+039B><U+0391><U+03A1><U+0399>S<U+0391> ", "<U+039B><U+0395><U+03A1><U+039F>S ", "<U+039B><U+0395><U+03A5><U+039A><U+0391><U+0394><U+0391> (<U+039D><U+0397>S<U+0399>) ", "<U+039B><U+0395>O<U+039D><U+0399><U+0394><U+0399><U+039F> ", "<U+039B><U+0397><U+039C><U+039D><U+039F>S ", "<U+039B><U+0399><U+0394>O<U+03A1><U+0399><U+039A><U+0399> ", "<U+039C><U+0391><U+039A><U+0395><U+0394><U+039F><U+039D><U+0399><U+0391> ", "<U+039C><U+0391><U+03A1><U+0391>TO<U+039D><U+0391>S ", "<U+039C><U+0395>TO<U+039D><U+0397> ", "<U+039C><U+0395>S<U+039F><U+039B><U+039F>GG<U+0399> ", "<U+039C><U+0397><U+039B><U+039F>S_<U+0391><U+039C>S ", "<U+039C><U+03A5><U+039A><U+039F><U+039D><U+039F>S ", "<U+039C><U+03A5><U+03A4><U+0399><U+039B><U+0397><U+039D><U+0397> ", "<U+039D><U+0391><U+039E><U+039F>S ", "<U+039D><U+0391><U+03A5><U+03A0><U+0391><U+039A><U+03A4><U+039F>S ", "<U+039D><U+0391><U+03A5><U+03A0><U+039B><U+0399><U+039F> ", "<U+039D><U+0395><U+0391> F<U+0399><U+039B><U+0391><U+0394><U+0395><U+039B>F<U+0395><U+0399><U+0391> ", "<U+039E><U+0391><U+039D>T<U+0397> ", "<U+039F><U+03A1><U+0395>S<U+03A4><U+0399><U+0391><U+0394><U+0391> ", "<U+03A0><U+0391><U+0399><U+0391><U+039D><U+0399><U+0391> ", "<U+03A0><U+0391><U+039B><U+0391><U+0399><U+039F><U+03A7>O<U+03A1><U+0391> ", "<U+03A0><U+0391><U+03A1><U+039F>S_<U+0391>/<U+0394> ", "<U+03A0><U+0391><U+03A4><U+03A1><U+0391> ", "<U+03A0><U+0395><U+0399><U+03A1><U+0391><U+0399><U+0391>S ", "<U+03A0><U+039F><U+039B><U+03A5>G<U+03A5><U+03A1><U+039F>S ", "<U+03A0><U+039F><U+03A4><U+0399><U+0394><U+0391><U+0399><U+0391> ", "<U+03A0><U+03A4><U+039F><U+039B><U+0395><U+039C><U+0391><U+0399><U+0394><U+0391> ", "<U+03A0><U+03A5><U+03A1>G<U+039F>S ", "<U+03A1><U+0391>F<U+0397><U+039D><U+0391> ", "<U+03A1><U+0395>T<U+03A5><U+039C><U+039D><U+039F> ", "<U+03A1><U+039F><U+0394><U+039F>S ", "S<U+0391><U+039C><U+039F>S ", "S<U+0395><U+0394><U+0395>S ", "S<U+0395><U+03A1><U+03A1><U+0395>S ", "S<U+0397><U+03A4><U+0395><U+0399><U+0391> ", "S<U+039A><U+0399><U+0391>T<U+039F>S ", "S<U+039A><U+039F><U+03A4><U+0399><U+039D><U+0391> ", "S<U+039A><U+03A5><U+03A1><U+039F>S ", "S<U+039F><U+03A5><U+0394><U+0391> ", "S<U+039F><U+03A5>F<U+039B><U+0399> ", "S<U+03A0><U+0391><U+03A1><U+03A4><U+0397> ", "S<U+03A0><U+0391><U+03A4><U+0391>(<U+0392><U+0395><U+039D><U+0399><U+0396><U+0395><U+039B><U+039F>S) ", "S<U+03A0><U+0395><U+03A4>S<U+0395>S ", "S<U+03A4><U+0395>F<U+0391><U+039D><U+0399> (<U+039A><U+039F><U+03A1><U+0399><U+039D>T<U+0399><U+0391>S) ", "S<U+03A5><U+039A><U+03A5>O<U+039D><U+0391> ", "S<U+03A5><U+03A1><U+039F>S_<U+0391>/<U+0394> ", "<U+03A4><U+0391><U+039D><U+0391>G<U+03A1><U+0391> ", "<U+03A4><U+0391><U+03A4><U+039F><U+0399> (<U+0394><U+0395><U+039A><U+0395><U+039B><U+0395><U+0399><U+0391>) ", "<U+03A4><U+0396><U+0395><U+03A1><U+039C><U+0399><U+0391><U+0394><U+0395>S ", "<U+03A4><U+03A1><U+0399><U+039A><U+0391><U+039B><U+0391> <U+0397><U+039C><U+0391>T<U+0395><U+0399><U+0391>S ", "<U+03A4><U+03A1><U+0399><U+039A><U+0391><U+039B><U+0391> T<U+0395>SS<U+0391><U+039B><U+0399><U+0391>S ", "<U+03A4><U+03A1><U+0399><U+03A0><U+039F><U+039B><U+0397> ", "<U+03A4><U+03A5><U+039C><U+03A0><U+0391><U+039A><U+0399> ", "<U+03A4><U+03A5><U+03A1><U+0399><U+039D>T<U+0391> ", "F<U+0391><U+03A1>S<U+0391><U+039B><U+0391> ", "F<U+039B>O<U+03A1><U+0399><U+039D><U+0391> ", "F<U+039F><U+03A5><U+03A1><U+039D><U+0397> ", "F<U+03A5><U+03A7><U+03A4><U+0399><U+0391> ", "<U+03A7><U+0391><U+039B><U+039A><U+0399><U+0394><U+0391> ", "<U+03A7><U+0391><U+039D><U+0399><U+0391> ", "<U+03A7><U+0399><U+039F>S ", "<U+03A7><U+03A1><U+03A5>S<U+039F><U+03A5><U+03A0><U+039F><U+039B><U+0397>_<U+039A><U+0391><U+0392><U+0391><U+039B><U+0391> ", "O<U+03A1><U+0395><U+039F><U+0399> " )

c（“G”， “GS”， “G”， “G”， “S”， "() ", " ", “S”， " ", " ", “OG”， “S”， “O”， “一般事务（G）”， “GS”， " () ", “（FT）”， “党卫军”， “党卫军”， “S”， “S”， “（TS）”， “S”， " ", “GS”， “GT”， “SF”， “S”， “S”， " ", “党卫军”， “S”， “ae”， “TS”， “TS_”， “S”， " ", “TSS”、“T（S）”， " ", "_/ ", “O”， " () ", “（GOS）”， " ", " ", " ", “S”， “TS_u/”， “TS_”， “S”， “党卫军”， “党卫军”， “S”， “S”， " ", " ", " ", “S”， “TS”， “T_/”， " ", “操作系统”、“操作系统”， " ", “S”， “S”， “（S）“， “O”， “S”， “O”， " ", “TOS”， “至”， “新加坡政府”， “S_S”， “S”， " ", “S”， “S”， " ", “FF”， “T”， “S”， " ", “O”， “S_/”， " ", “S”， “GS”， " ", " ", “GS”， “F”， “T”， “S”， “党卫军”， “党卫军”， “党卫军”， “S”， “STS”， “S”， “党卫军”， “S”， “SF”， “S”， “S（S）”， “SSS”， “SF（TS）”， “所以”， “SS_uu/”， “G”， " () ", “S”， “TS”， “TSSS”， " ", " ", “T”， “财政司司长”， “FO”， “F”， “F”， " ", " ", “S”， “S_”， “O” )
您所拥有的看起来像是普通的7位ASCII字符，并尝试通过将其中一些代码点包装为：
来编码Unicode代码点

据我所知，这不是一种公认的Unicode编码，部分原因是您如何放置一个真正的
。我已经在base R中编写了一个方便、通用且内部有点不稳定的函数，用于此目的。它是： dsub <- function(input,re,f=function(s,d) paste0(s,c(if (length(d)==0L) NULL else paste0('<',d,'>'),''),collapse='')) { splits <- strsplit(input,re,perl=T); delims <- lapply(strsplit(gsub(paste0('(',re,')'),'.\\1',input,perl=T),paste0('\\.(?=',re,')'),perl=T),function(x) sub(paste0('^(',re,').*'),'\\1',x[-1],perl=T)) lapply(1:length(splits), function(i) { s <- splits[[i]]; d <- delims[[i]]; f(c(s,if (length(s)==length(d)) '' else NULL),d); } ); }; 并使用本问题中给出的相当广泛的示例数据： input <- c("<U+0391>G<U+03A1><U+0399><..."); ## (excerpted) do.call(c,dsub(input,re,f)); ## [1] "ΑGΡΙΝΙΟ " "ΑGΧΙΑΛΟS " "ΑΙGΙΝΑ " "ΑΙGΙΟ " ## [5] "ΑΙΔΗΨΟS " "ΑΚΤΙΟ(ΠΡΕΒΕΖΑ) " "ΑΛΕΞΑΝΔΡΟΥΠΟΛΗ " "ΑΛΙΑΡΤΟS " ## [9] "ΑΝΑΒΡΥΤΑ " "ΑΝΔΡΑΒΙΔΑ " "ΑΝOGΕΙΑ " "ΑΡΑΞΟS " ## [13] "ΑΡΑΧOΒΑ " "ΑΡGΟS(ΠΥΡGΕΛΑ) " "ΑΡGΟSΤΟΛΙ " "ΑΡΤΑ (ΠΟΛΗ) " ## [17] "ΑΡΤΑ (FΙΛΟTΕΗ) " "ΑSΤΕΡΟSΚΟΠΕΙΟ " "ΑSΤΡΟS " "ΑSΤΥΠΑΛΑΙΑ " ## [21] "ΒΑΜΟS " "ΒΕΛΟ (ΚΟΡΙΝTΙΑS) " "ΒΟΛΟS " "ΒΥΤΙΝΑ " ## [25] "GΟΡΤΥS " "GΥTΕΙΟ " "ΔΕSFΙΝΑ " "ΔΙΑΒΟΛΙΤSΙ " ## [29] "ΔΟΜΟΚΟS " "ΔΡΑΜΑ " "ΕΔΕSSΑ " "ΕΛΕΥSΙΝΑ " ## [33] "ΕΛΛΗΝΙΚΟ aeρ " "ΖΑΚΥΝTΟS " "ΖΑΚΥΝTΟS_ΠΟΛΗ " "ΖΑΡΟS " ## [37] "ΗΡΑΚΛΕΙΟ " "TΑSΟS " "TΗΡΑ (SΑΝΤΟΡΙΝΗ" "ΙΕΡΑΠΕΤΡΑ " ## [41] "ΙΚΑΡΙΑ_Α/Δ " "ΙOΑΝΝΙΝΑ " "ΚΑΒΑΛΑ (ΠΟΛΗ) " "ΚΑΒΑΛΑ(ΑΜΥGΔΑΛΕOΝΑS) " ## [45] "ΚΑΛΑΒΡΥΤΑ " "ΚΑΛΑΜΑΤΑ " "ΚΑΛΑΜΠΑΚΑ " "ΚΑΡΔΙΤSΑ " ## [49] "ΚΑΡΠΑTΟS_Α/Δ " "ΚΑΡΠΑTΟS_ΠΟΛΗ " "ΚΑΡΠΕΝΗSΙ " "ΚΑΡΥSΤΟS " ## [53] "ΚΑSΟS " "ΚΑSΤΕΛΛΙ " "ΚΑSΤΟΡΙΑ " "ΚΕΡΚΥΡΑ " ## [57] "ΚΟΖΑΝΗ " "ΚΟΜΟΤΗΝΗ " "ΚΟΝΙΤSΑ " "ΚΟΡΙΝTΟS " ## [61] "ΚΥTΗΡΑ_Α/Δ " "ΚΥΜΗ " "ΚOS " "ΚOS_ΠΟΛΗ " ## [65] "ΛΑΜΙΑ " "ΛΑΡΙSΑ " "ΛΕΡΟS " "ΛΕΥΚΑΔΑ (ΝΗSΙ) " ## [69] "ΛΕOΝΙΔΙΟ " "ΛΗΜΝΟS " "ΛΙΔOΡΙΚΙ " "ΜΑΚΕΔΟΝΙΑ " ## [73] "ΜΑΡΑTOΝΑS " "ΜΕTOΝΗ " "ΜΕSΟΛΟGGΙ " "ΜΗΛΟS_ΑΜS " ## [77] "ΜΥΚΟΝΟS " "ΜΥΤΙΛΗΝΗ " "ΝΑΞΟS " "ΝΑΥΠΑΚΤΟS " ## [81] "ΝΑΥΠΛΙΟ " "ΝΕΑ FΙΛΑΔΕΛFΕΙΑ " "ΞΑΝTΗ " "ΟΡΕSΤΙΑΔΑ " ## [85] "ΠΑΙΑΝΙΑ " "ΠΑΛΑΙΟΧOΡΑ " "ΠΑΡΟS_Α/Δ " "ΠΑΤΡΑ " ## [89] "ΠΕΙΡΑΙΑS " "ΠΟΛΥGΥΡΟS " "ΠΟΤΙΔΑΙΑ " "ΠΤΟΛΕΜΑΙΔΑ " ## [93] "ΠΥΡGΟS " "ΡΑFΗΝΑ " "ΡΕTΥΜΝΟ " "ΡΟΔΟS " ## [97] "SΑΜΟS " "SΕΔΕS " "SΕΡΡΕS " "SΗΤΕΙΑ " ## [101] "SΚΙΑTΟS " "SΚΟΤΙΝΑ " "SΚΥΡΟS " "SΟΥΔΑ " ## [105] "SΟΥFΛΙ " "SΠΑΡΤΗ " "SΠΑΤΑ(ΒΕΝΙΖΕΛΟS) " "SΠΕΤSΕS " ## [109] "SΤΕFΑΝΙ (ΚΟΡΙΝTΙΑS) " "SΥΚΥOΝΑ " "SΥΡΟS_Α/Δ " "ΤΑΝΑGΡΑ " ## [113] "ΤΑΤΟΙ (ΔΕΚΕΛΕΙΑ) " "ΤΖΕΡΜΙΑΔΕS " "ΤΡΙΚΑΛΑ ΗΜΑTΕΙΑS " "ΤΡΙΚΑΛΑ TΕSSΑΛΙΑS " ## [117] "ΤΡΙΠΟΛΗ " "ΤΥΜΠΑΚΙ " "ΤΥΡΙΝTΑ " "FΑΡSΑΛΑ " ## [121] "FΛOΡΙΝΑ " "FΟΥΡΝΗ " "FΥΧΤΙΑ " "ΧΑΛΚΙΔΑ " ## [125] "ΧΑΝΙΑ " "ΧΙΟS " "ΧΡΥSΟΥΠΟΛΗ_ΚΑΒΑΛΑ " "OΡΕΟΙ " input这里有另一种方法来恢复字符串中编码的真正未编码字符（借用自）。在这里，我们仔细匹配表单，并通过一些位操作将该十六进制值展开为适当大小的unicode字符 trueunicode <- function(x) { packuni<-Vectorize(function(cp) { bv <- intToBits(cp) maxbit <- tail(which(bv!=as.raw(0)),1) if(maxbit < 8) { rawToChar(as.raw(codepoint)) } else if (maxbit < 12) { rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:11], as.raw(c(0,1,1))), "raw"))) } else if (maxbit < 17){ rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:12], as.raw(c(0,1)), bv[13:16], as.raw(c(0,1,1,1))), "raw"))) } else { stop("too many bits") } }) m <- gregexpr("<U\\+[0-9a-fA-F]{4}>", x) codes <- regmatches(x,m) chars <- lapply(codes, function(x) { codepoints <- strtoi(paste0("0x", substring(x,4,7))) packuni(codepoints) }) regmatches(x,m) <- chars Encoding(x)<-"UTF-8" x } @不管你引用不引用Spacedman的话，问题都是一样的。有什么想法吗？想法：基本上你已经搞得一团糟了。一些 dsub <- function(input,re,f=function(s,d) paste0(s,c(if (length(d)==0L) NULL else paste0('<',d,'>'),''),collapse='')) { splits <- strsplit(input,re,perl=T); delims <- lapply(strsplit(gsub(paste0('(',re,')'),'.\\1',input,perl=T),paste0('\\.(?=',re,')'),perl=T),function(x) sub(paste0('^(',re,').*'),'\\1',x[-1],perl=T)) lapply(1:length(splits), function(i) { s <- splits[[i]]; d <- delims[[i]]; f(c(s,if (length(s)==length(d)) '' else NULL),d); } ); }; input <- c('Luc TR<U+00c9>HAN','aa<U+00ca>bb<U+00cb>cc','<U+00CC><U+00Cd>','',' '); re <- '<U\\+([0-9a-fA-F]{4})>'; f <- function(s,d) paste0(s,c(if (length(d)==0L) NULL else intToUtf8(paste0('0x',sub(re,'\\1',d)),multiple=T),''),collapse=''); do.call(c,dsub(input,re,f)); ## [1] "Luc TRÉHAN" "aaÊbbËcc" "ÌÍ" "" " " input <- c("<U+0391>G<U+03A1><U+0399><..."); ## (excerpted) do.call(c,dsub(input,re,f)); ## [1] "ΑGΡΙΝΙΟ " "ΑGΧΙΑΛΟS " "ΑΙGΙΝΑ " "ΑΙGΙΟ " ## [5] "ΑΙΔΗΨΟS " "ΑΚΤΙΟ(ΠΡΕΒΕΖΑ) " "ΑΛΕΞΑΝΔΡΟΥΠΟΛΗ " "ΑΛΙΑΡΤΟS " ## [9] "ΑΝΑΒΡΥΤΑ " "ΑΝΔΡΑΒΙΔΑ " "ΑΝOGΕΙΑ " "ΑΡΑΞΟS " ## [13] "ΑΡΑΧOΒΑ " "ΑΡGΟS(ΠΥΡGΕΛΑ) " "ΑΡGΟSΤΟΛΙ " "ΑΡΤΑ (ΠΟΛΗ) " ## [17] "ΑΡΤΑ (FΙΛΟTΕΗ) " "ΑSΤΕΡΟSΚΟΠΕΙΟ " "ΑSΤΡΟS " "ΑSΤΥΠΑΛΑΙΑ " ## [21] "ΒΑΜΟS " "ΒΕΛΟ (ΚΟΡΙΝTΙΑS) " "ΒΟΛΟS " "ΒΥΤΙΝΑ " ## [25] "GΟΡΤΥS " "GΥTΕΙΟ " "ΔΕSFΙΝΑ " "ΔΙΑΒΟΛΙΤSΙ " ## [29] "ΔΟΜΟΚΟS " "ΔΡΑΜΑ " "ΕΔΕSSΑ " "ΕΛΕΥSΙΝΑ " ## [33] "ΕΛΛΗΝΙΚΟ aeρ " "ΖΑΚΥΝTΟS " "ΖΑΚΥΝTΟS_ΠΟΛΗ " "ΖΑΡΟS " ## [37] "ΗΡΑΚΛΕΙΟ " "TΑSΟS " "TΗΡΑ (SΑΝΤΟΡΙΝΗ" "ΙΕΡΑΠΕΤΡΑ " ## [41] "ΙΚΑΡΙΑ_Α/Δ " "ΙOΑΝΝΙΝΑ " "ΚΑΒΑΛΑ (ΠΟΛΗ) " "ΚΑΒΑΛΑ(ΑΜΥGΔΑΛΕOΝΑS) " ## [45] "ΚΑΛΑΒΡΥΤΑ " "ΚΑΛΑΜΑΤΑ " "ΚΑΛΑΜΠΑΚΑ " "ΚΑΡΔΙΤSΑ " ## [49] "ΚΑΡΠΑTΟS_Α/Δ " "ΚΑΡΠΑTΟS_ΠΟΛΗ " "ΚΑΡΠΕΝΗSΙ " "ΚΑΡΥSΤΟS " ## [53] "ΚΑSΟS " "ΚΑSΤΕΛΛΙ " "ΚΑSΤΟΡΙΑ " "ΚΕΡΚΥΡΑ " ## [57] "ΚΟΖΑΝΗ " "ΚΟΜΟΤΗΝΗ " "ΚΟΝΙΤSΑ " "ΚΟΡΙΝTΟS " ## [61] "ΚΥTΗΡΑ_Α/Δ " "ΚΥΜΗ " "ΚOS " "ΚOS_ΠΟΛΗ " ## [65] "ΛΑΜΙΑ " "ΛΑΡΙSΑ " "ΛΕΡΟS " "ΛΕΥΚΑΔΑ (ΝΗSΙ) " ## [69] "ΛΕOΝΙΔΙΟ " "ΛΗΜΝΟS " "ΛΙΔOΡΙΚΙ " "ΜΑΚΕΔΟΝΙΑ " ## [73] "ΜΑΡΑTOΝΑS " "ΜΕTOΝΗ " "ΜΕSΟΛΟGGΙ " "ΜΗΛΟS_ΑΜS " ## [77] "ΜΥΚΟΝΟS " "ΜΥΤΙΛΗΝΗ " "ΝΑΞΟS " "ΝΑΥΠΑΚΤΟS " ## [81] "ΝΑΥΠΛΙΟ " "ΝΕΑ FΙΛΑΔΕΛFΕΙΑ " "ΞΑΝTΗ " "ΟΡΕSΤΙΑΔΑ " ## [85] "ΠΑΙΑΝΙΑ " "ΠΑΛΑΙΟΧOΡΑ " "ΠΑΡΟS_Α/Δ " "ΠΑΤΡΑ " ## [89] "ΠΕΙΡΑΙΑS " "ΠΟΛΥGΥΡΟS " "ΠΟΤΙΔΑΙΑ " "ΠΤΟΛΕΜΑΙΔΑ " ## [93] "ΠΥΡGΟS " "ΡΑFΗΝΑ " "ΡΕTΥΜΝΟ " "ΡΟΔΟS " ## [97] "SΑΜΟS " "SΕΔΕS " "SΕΡΡΕS " "SΗΤΕΙΑ " ## [101] "SΚΙΑTΟS " "SΚΟΤΙΝΑ " "SΚΥΡΟS " "SΟΥΔΑ " ## [105] "SΟΥFΛΙ " "SΠΑΡΤΗ " "SΠΑΤΑ(ΒΕΝΙΖΕΛΟS) " "SΠΕΤSΕS " ## [109] "SΤΕFΑΝΙ (ΚΟΡΙΝTΙΑS) " "SΥΚΥOΝΑ " "SΥΡΟS_Α/Δ " "ΤΑΝΑGΡΑ " ## [113] "ΤΑΤΟΙ (ΔΕΚΕΛΕΙΑ) " "ΤΖΕΡΜΙΑΔΕS " "ΤΡΙΚΑΛΑ ΗΜΑTΕΙΑS " "ΤΡΙΚΑΛΑ TΕSSΑΛΙΑS " ## [117] "ΤΡΙΠΟΛΗ " "ΤΥΜΠΑΚΙ " "ΤΥΡΙΝTΑ " "FΑΡSΑΛΑ " ## [121] "FΛOΡΙΝΑ " "FΟΥΡΝΗ " "FΥΧΤΙΑ " "ΧΑΛΚΙΔΑ " ## [125] "ΧΑΝΙΑ " "ΧΙΟS " "ΧΡΥSΟΥΠΟΛΗ_ΚΑΒΑΛΑ " "OΡΕΟΙ " trueunicode <- function(x) { packuni<-Vectorize(function(cp) { bv <- intToBits(cp) maxbit <- tail(which(bv!=as.raw(0)),1) if(maxbit < 8) { rawToChar(as.raw(codepoint)) } else if (maxbit < 12) { rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:11], as.raw(c(0,1,1))), "raw"))) } else if (maxbit < 17){ rawToChar(rev(packBits(c(bv[1:6], as.raw(c(0,1)), bv[7:12], as.raw(c(0,1)), bv[13:16], as.raw(c(0,1,1,1))), "raw"))) } else { stop("too many bits") } }) m <- gregexpr("<U\\+[0-9a-fA-F]{4}>", x) codes <- regmatches(x,m) chars <- lapply(codes, function(x) { codepoints <- strtoi(paste0("0x", substring(x,4,7))) packuni(codepoints) }) regmatches(x,m) <- chars Encoding(x)<-"UTF-8" x } input <- c("<U+0391>G<U+03A1><U+0399><U+039D><U+0399><U+039F>", "<U+0391>G<U+03A7><U+0399><U+0391><U+039B><U+039F>S","<U+0391><U+0399>G<U+0399><U+039D><U+0391>", "<U+0391><U+0399>G<U+0399><U+039F>", "<U+0391><U+0399><U+0394><U+0397><U+03A8><U+039F>S","<U+0391><U+039A><U+03A4><U+0399><U+039F>(<U+03A0><U+03A1><U+0395><U+0392><U+0395><U+0396><U+0391>)") trueunicode(input) # [1] "ΑGΡΙΝΙΟ" "ΑGΧΙΑΛΟS" "ΑΙGΙΝΑ" "ΑΙGΙΟ" # [5] "ΑΙΔΗΨΟS" "ΑΚΤΙΟ(ΠΡΕΒΕΖΑ)"