Difference between revisions of "Statistics"

From BaseX Documentation
Jump to navigation Jump to search
m (Removed redundant section (double "Sources" section), did a diff on them ...)
Line 6: Line 6:
  
 
== Databases ==
 
== Databases ==
<table style="margin:0px; padding:0px;" border="0" cellspacing="0">
+
{| class="wikitable sortable"
<tr><td width="120"><b>Instances &nbsp; &nbsp;</b></td><td width="80"><b>file size</b></td><td width="80"><b>db size</b></td><td width="110"><b>#nodes &nbsp;</b></td><td><b>#atr &nbsp;</b></td><td><b>#eln &nbsp;</b></td><td><b>#atn &nbsp;</b></td><td><b>#uri &nbsp;</b></td><td><b>height &nbsp;</b></td><td><b>#docs &nbsp;</b></td></tr>
+
|-
<tr><td>RuWikiHist</td><td>421 GiB</td><td>416 GiB</td><td>324,848,508</td><td>3</td><td>21</td><td>6</td><td>2</td><td>6</td><td>1</td></tr>
+
!Instances
<tr><td>ZhWikiHist</td><td>126 GiB</td><td>120 GiB</td><td>179,199,662</td><td>3</td><td>21</td><td>6</td><td>2</td><td>6</td><td>1</td></tr>
+
!file size  
<tr><td>EnWiktionary</td><td>79 GiB</td><td>75 GiB</td><td>134,380,393</td><td>3</td><td>21</td><td>6</td><td>2</td><td>6</td><td>1</td></tr>
+
!#files
<tr><td>XMark</td><td>55 GiB</td><td>64 GiB</td><td>1,615,071,348</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
!db size  
<tr><td>EnWikiMeta</td><td>54 GiB</td><td>52 GiB</td><td>401,456,348</td><td>3</td><td>21</td><td>6</td><td>2</td><td>6</td><td>1</td></tr>
+
!#db nodes  
<tr><td>MedLine</td><td>38 GiB</td><td>36 GiB</td><td>1,623,764,254</td><td>2</td><td>84</td><td>6</td><td>0</td><td>9</td><td>379</td></tr>
+
!#atr  
<tr><td>iProClass</td><td>36 GiB</td><td>37 GiB</td><td>1,631,218,984</td><td>3</td><td>245</td><td>4</td><td>2</td><td>9</td><td>1</td></tr>
+
!#eln  
<tr><td>Inex209</td><td>31 GiB</td><td>34 GiB</td><td>1,336,110,639</td><td>15</td><td>28,034</td><td>451</td><td>1</td><td>37</td><td>2,666,500</td></tr>
+
!#atn  
<tr><td>CoPhIR</td><td>29 GiB</td><td>31 GiB</td><td>1,104,623,376</td><td>10</td><td>42</td><td>42</td><td>0</td><td>8</td><td>10,000,000</td></tr>
+
!#uri
<tr><td>EnWikipedia</td><td>26 GiB</td><td>25 GiB</td><td>198,546,747</td><td>3</td><td>24</td><td>21</td><td>2</td><td>6</td><td>1</td></tr>
+
!height
<tr><td>XMark</td><td>22 GiB</td><td>26 GiB</td><td>645,997,965</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
|-
<tr><td>InterPro</td><td>14 GiB</td><td>19 GiB</td><td>860,304,235</td><td>5</td><td>7</td><td>15</td><td>0</td><td>4</td><td>1</td></tr>
+
| RuWikiHist  
<tr><td>Genome1</td><td>13 GiB</td><td>13 GiB</td><td>432,628,105</td><td>12</td><td>26</td><td>101</td><td>2</td><td>6</td><td>1</td></tr>
+
|421 GiB  
<tr><td>NewYorkTimes</td><td>12 GiB</td><td>13 GiB</td><td>280,407,005</td><td>5</td><td>41</td><td>33</td><td>0</td><td>6</td><td>1,855,659</td></tr>
+
|1
<tr><td>TrEMBL</td><td>11 GiB</td><td>14 GiB</td><td>589,650,535</td><td>8</td><td>47</td><td>30</td><td>2</td><td>7</td><td>1</td></tr>
+
|416 GiB  
<tr><td>XMark</td><td>11 GiB</td><td>13 GiB</td><td>323,083,409</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
|324,848,508  
<tr><td>IntAct</td><td>7973 MiB</td><td>6717 MiB</td><td>297,478,392</td><td>7</td><td>64</td><td>22</td><td>2</td><td>14</td><td>25,624</td></tr>
+
|3  
<tr><td>Freebase</td><td>7366 MiB</td><td>10 GiB</td><td>443,627,994</td><td>8</td><td>61</td><td>283</td><td>1</td><td>93</td><td>1</td></tr>
+
|21  
<tr><td>SDMX</td><td>6356 MiB</td><td>8028 MiB</td><td>395,871,872</td><td>2</td><td>22</td><td>6</td><td>3</td><td>7</td><td>1</td></tr>
+
|6  
<tr><td>OpenStreetMap</td><td>5312 MiB</td><td>5171 MiB</td><td>6,910,669</td><td>3</td><td>19</td><td>5</td><td>2</td><td>6</td><td>1</td></tr>
+
|2  
<tr><td>SwissProt</td><td>4604 MiB</td><td>5422 MiB</td><td>241,274,406</td><td>8</td><td>70</td><td>39</td><td>2</td><td>7</td><td>1</td></tr>
+
|6  
<tr><td>EURLex</td><td>4815 MiB</td><td>5532 MiB</td><td>167,328,039</td><td>23</td><td>186</td><td>46</td><td>1</td><td>12</td><td>1</td></tr>
+
|-
<tr><td>Wikicorpus</td><td>4492 MiB</td><td>4432 MiB</td><td>157,948,561</td><td>12</td><td>1,257</td><td>2,687</td><td>2</td><td>50</td><td>659,338</td></tr>
+
| ZhWikiHist
<tr><td>EnWikiRDF</td><td>3679 MiB</td><td>3537 MiB</td><td>98,433,194</td><td>1</td><td>11</td><td>2</td><td>11</td><td>4</td><td>1</td></tr>
+
| 126 GiB
<tr><td>CoPhIR</td><td>2695 MiB</td><td>2882 MiB</td><td>101,638,857</td><td>10</td><td>42</td><td>42</td><td>0</td><td>8</td><td>1,000,000</td></tr>
+
| 1
<tr><td>MeSH</td><td>2091 MiB</td><td>2410 MiB</td><td>104,845,819</td><td>3</td><td>6</td><td>5</td><td>2</td><td>5</td><td>1</td></tr>
+
| 120 GiB
<tr><td>FreeDB</td><td>1723 MiB</td><td>2462 MiB</td><td>102,901,519</td><td>2</td><td>7</td><td>3</td><td>0</td><td>4</td><td>1</td></tr>
+
| 179,199,662
<tr><td>XMark</td><td>1134 MiB</td><td>1303 MiB</td><td>32,298,989</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
| 3
<tr><td>DeepFS</td><td>810 MiB</td><td>850 MiB</td><td>44,821,506</td><td>4</td><td>3</td><td>6</td><td>0</td><td>24</td><td>1</td></tr>
+
| 21
<tr><td>LibraryUKN</td><td>760 MiB</td><td>918 MiB</td><td>46,401,941</td><td>3</td><td>23</td><td>3</td><td>0</td><td>5</td><td>1</td></tr>
+
| 6
<tr><td>Twitter</td><td>736 MiB</td><td>767 MiB</td><td>15,309,015</td><td>0</td><td>8</td><td>0</td><td>0</td><td>3</td><td>1,177,495</td></tr>
+
| 2
<tr><td>Organizations</td><td>733 MiB</td><td>724 MiB</td><td>33,112,392</td><td>3</td><td>38</td><td>9</td><td>0</td><td>7</td><td>1,019,132</td></tr>
+
| 6
<tr><td>DBLP</td><td>694 MiB</td><td>944 MiB</td><td>36,878,181</td><td>4</td><td>35</td><td>6</td><td>0</td><td>7</td><td>1</td></tr>
+
|-
<tr><td>Feeds</td><td>692 MiB</td><td>604 MiB</td><td>5,933,713</td><td>0</td><td>8</td><td>0</td><td>0</td><td>3</td><td>444,014</td></tr>
+
| EnWiktionary
<tr><td>MedLineSupp</td><td>477 MiB</td><td>407 MiB</td><td>21,602,141</td><td>5</td><td>55</td><td>7</td><td>0</td><td>9</td><td>1</td></tr>
+
| 79 GiB
<tr><td>AirBase</td><td>449 MiB</td><td>273 MiB</td><td>14,512,851</td><td>1</td><td>111</td><td>5</td><td>0</td><td>11</td><td>38</td></tr>
+
| 1
<tr><td>MedLineDesc</td><td>260 MiB</td><td>195 MiB</td><td>10,401,847</td><td>5</td><td>66</td><td>8</td><td>0</td><td>9</td><td>1</td></tr>
+
| 75 GiB
<tr><td>ZDNET</td><td>130 MiB</td><td>133 MiB</td><td>3,060,186</td><td>21</td><td>40</td><td>90</td><td>0</td><td>13</td><td>95,663</td></tr>
+
| 134,380,393
<tr><td>JMNEdict</td><td>124 MiB</td><td>171 MiB</td><td>8,592,666</td><td>0</td><td>10</td><td>0</td><td>0</td><td>5</td><td>1</td></tr>
+
| 3
<tr><td>XMark</td><td>111 MiB</td><td>130 MiB</td><td>3,221,926</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
| 21
<tr><td>Freshmeat</td><td>105 MiB</td><td>86 MiB</td><td>3,832,028</td><td>1</td><td>58</td><td>1</td><td>0</td><td>6</td><td>1</td></tr>
+
| 6
<tr><td>DeepFS</td><td>83 MiB</td><td>93 MiB</td><td>4,842,638</td><td>4</td><td>3</td><td>6</td><td>0</td><td>21</td><td>1</td></tr>
+
| 2
<tr><td>Treebank</td><td>82 MiB</td><td>92 MiB</td><td>3,829,513</td><td>1</td><td>250</td><td>1</td><td>0</td><td>37</td><td>1</td></tr>
+
| 6
<tr><td>DBLP2</td><td>80 MiB</td><td>102 MiB</td><td>4,044,649</td><td>4</td><td>35</td><td>6</td><td>0</td><td>6</td><td>170,843</td></tr>
+
|-
<tr><td>DDI</td><td>76 MiB</td><td>39 MiB</td><td>2,070,157</td><td>7</td><td>104</td><td>16</td><td>21</td><td>11</td><td>3</td></tr>
+
| XMark
<tr><td>Alfred</td><td>75 MiB</td><td>68 MiB</td><td>3,784,285</td><td>0</td><td>60</td><td>0</td><td>0</td><td>6</td><td>1</td></tr>
+
| 55 GiB
<tr><td>University</td><td>56 MiB</td><td>66 MiB</td><td>3,468,606</td><td>1</td><td>28</td><td>4</td><td>0</td><td>5</td><td>6</td></tr>
+
| 1
<tr><td>MediaUKN</td><td>38 MiB</td><td>45 MiB</td><td>1,619,443</td><td>3</td><td>21</td><td>3</td><td>0</td><td>5</td><td>1</td></tr>
+
| 64 GiB
<tr><td>HCIBIB2</td><td>32 MiB</td><td>33 MiB</td><td>617,023</td><td>1</td><td>39</td><td>1</td><td>0</td><td>4</td><td>26,390</td></tr>
+
| 1,615,071,348
<tr><td>Nasa</td><td>24 MiB</td><td>25 MiB</td><td>845,805</td><td>2</td><td>61</td><td>8</td><td>1</td><td>9</td><td>1</td></tr>
+
| 2
<tr><td>MovieDB</td><td>16 MiB</td><td>19 MiB</td><td>868,980</td><td>6</td><td>7</td><td>8</td><td>0</td><td>4</td><td>1</td></tr>
+
| 74
<tr><td>KanjiDic2</td><td>13 MiB</td><td>18 MiB</td><td>917,833</td><td>3</td><td>27</td><td>10</td><td>0</td><td>6</td><td>1</td></tr>
+
| 9
<tr><td>XMark</td><td>11 MiB</td><td>13 MiB</td><td>324,274</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
| 0
<tr><td>Shakespeare</td><td>7711 KiB</td><td>9854 KiB</td><td>327,170</td><td>0</td><td>59</td><td>0</td><td>0</td><td>9</td><td>1</td></tr>
+
| 13
<tr><td>TreeOfLife</td><td>5425 KiB</td><td>7106 KiB</td><td>363,560</td><td>7</td><td>4</td><td>7</td><td>0</td><td>243</td><td>1</td></tr>
+
|-
<tr><td>Thesaurus</td><td>4288 KiB</td><td>4088 KiB</td><td>201,798</td><td>7</td><td>33</td><td>9</td><td>0</td><td>7</td><td>1</td></tr>
+
| EnWikiMeta
<tr><td>MusicXML</td><td>3155 KiB</td><td>2942 KiB</td><td>171,400</td><td>8</td><td>179</td><td>56</td><td>0</td><td>8</td><td>17</td></tr>
+
| 54 GiB
<tr><td>BibDBPub</td><td>2292 KiB</td><td>2359 KiB</td><td>80,178</td><td>1</td><td>54</td><td>1</td><td>0</td><td>4</td><td>3,465</td></tr>
+
| 1
<tr><td>Factbook</td><td>1743 KiB</td><td>1560 KiB</td><td>77,315</td><td>16</td><td>23</td><td>32</td><td>0</td><td>6</td><td>1</td></tr>
+
| 52 GiB
<tr><td>XMark</td><td>1134 KiB</td><td>1334 KiB</td><td>33,056</td><td>2</td><td>74</td><td>9</td><td>0</td><td>13</td><td>1</td></tr>
+
| 401,456,348
</table>
+
| 3
 +
| 21
 +
| 6
 +
| 2
 +
| 6
 +
|-
 +
| MedLine
 +
| 38 GiB
 +
| 379
 +
| 36 GiB
 +
| 1,623,764,254
 +
| 2
 +
| 84
 +
| 6
 +
| 0
 +
| 9
 +
|-
 +
| iProClass
 +
| 36 GiB
 +
| 1
 +
| 37 GiB
 +
| 1,631,218,984
 +
| 3
 +
| 245
 +
| 4
 +
| 2
 +
| 9
 +
|-
 +
| Inex209
 +
| 31 GiB
 +
| 2,666,500
 +
| 34 GiB
 +
| 1,336,110,639
 +
| 15
 +
| 28,034
 +
| 451
 +
| 1
 +
| 37
 +
|-
 +
| CoPhIR
 +
| 29 GiB
 +
| 10,000,000
 +
| 31 GiB
 +
| 1,104,623,376
 +
| 10
 +
| 42
 +
| 42
 +
| 0
 +
| 8
 +
|-
 +
| EnWikipedia
 +
| 26 GiB
 +
| 1
 +
| 25 GiB
 +
| 198,546,747
 +
| 3
 +
| 24
 +
| 21
 +
| 2
 +
| 6
 +
|-
 +
| XMark
 +
| 22 GiB
 +
| 1
 +
| 26 GiB
 +
| 645,997,965
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|-
 +
| InterPro
 +
| 14 GiB
 +
| 1
 +
| 19 GiB
 +
| 860,304,235
 +
| 5
 +
| 7
 +
| 15
 +
| 0
 +
| 4
 +
|-
 +
| Genome1
 +
| 13 GiB
 +
| 1
 +
| 13 GiB
 +
| 432,628,105
 +
| 12
 +
| 26
 +
| 101
 +
| 2
 +
| 6
 +
|-
 +
| NewYorkTimes
 +
| 12 GiB
 +
| 1,855,659
 +
| 13 GiB
 +
| 280,407,005
 +
| 5
 +
| 41
 +
| 33
 +
| 0
 +
| 6
 +
|-
 +
| TrEMBL
 +
| 11 GiB
 +
| 1
 +
| 14 GiB
 +
| 589,650,535
 +
| 8
 +
| 47
 +
| 30
 +
| 2
 +
| 7
 +
|-
 +
| XMark
 +
| 11 GiB
 +
| 1
 +
| 13 GiB
 +
| 323,083,409
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|-
 +
| IntAct
 +
| 7973 MiB
 +
| 25,624
 +
| 6717 MiB
 +
| 297,478,392
 +
| 7
 +
| 64
 +
| 22
 +
| 2
 +
| 14
 +
|-
 +
| Freebase
 +
| 7366 MiB
 +
| 1
 +
| 10 GiB
 +
| 443,627,994
 +
| 8
 +
| 61
 +
| 283
 +
| 1
 +
| 93
 +
|-
 +
| SDMX
 +
| 6356 MiB
 +
| 1
 +
| 8028 MiB
 +
| 395,871,872
 +
| 2
 +
| 22
 +
| 6
 +
| 3
 +
| 7
 +
|-
 +
| OpenStreetMap
 +
| 5312 MiB
 +
| 1
 +
| 5171 MiB
 +
| 6,910,669
 +
| 3
 +
| 19
 +
| 5
 +
| 2
 +
| 6
 +
|-
 +
| SwissProt
 +
| 4604 MiB
 +
| 1
 +
| 5422 MiB
 +
| 241,274,406
 +
| 8
 +
| 70
 +
| 39
 +
| 2
 +
| 7
 +
|-
 +
| EURLex
 +
| 4815 MiB
 +
| 1
 +
| 5532 MiB
 +
| 167,328,039
 +
| 23
 +
| 186
 +
| 46
 +
| 1
 +
| 12
 +
|-
 +
| Wikicorpus
 +
| 4492 MiB
 +
| 659,338
 +
| 4432 MiB
 +
| 157,948,561
 +
| 12
 +
| 1,257
 +
| 2,687
 +
| 2
 +
| 50
 +
|-
 +
| EnWikiRDF
 +
| 3679 MiB
 +
| 1
 +
| 3537 MiB
 +
| 98,433,194
 +
| 1
 +
| 11
 +
| 2
 +
| 11
 +
| 4
 +
|-
 +
| CoPhIR
 +
| 2695 MiB
 +
| 1,000,000
 +
| 2882 MiB
 +
| 101,638,857
 +
| 10
 +
| 42
 +
| 42
 +
| 0
 +
| 8
 +
|-
 +
| MeSH
 +
| 2091 MiB
 +
| 1
 +
| 2410 MiB
 +
| 104,845,819
 +
| 3
 +
| 6
 +
| 5
 +
| 2
 +
| 5
 +
|-
 +
| FreeDB
 +
| 1723 MiB
 +
| 1
 +
| 2462 MiB
 +
| 102,901,519
 +
| 2
 +
| 7
 +
| 3
 +
| 0
 +
| 4
 +
|-
 +
| XMark
 +
| 1134 MiB
 +
| 1
 +
| 1303 MiB
 +
| 32,298,989
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|-
 +
| DeepFS
 +
| 810 MiB
 +
| 1
 +
| 850 MiB
 +
| 44,821,506
 +
| 4
 +
| 3
 +
| 6
 +
| 0
 +
| 24
 +
|-
 +
| LibraryUKN
 +
| 760 MiB
 +
| 1
 +
| 918 MiB
 +
| 46,401,941
 +
| 3
 +
| 23
 +
| 3
 +
| 0
 +
| 5
 +
|-
 +
| Twitter
 +
| 736 MiB
 +
| 1,177,495
 +
| 767 MiB
 +
| 15,309,015
 +
| 0
 +
| 8
 +
| 0
 +
| 0
 +
| 3
 +
|-
 +
| Organizations
 +
| 733 MiB
 +
| 1,019,132
 +
| 724 MiB
 +
| 33,112,392
 +
| 3
 +
| 38
 +
| 9
 +
| 0
 +
| 7
 +
|-
 +
| DBLP
 +
| 694 MiB
 +
| 1
 +
| 944 MiB
 +
| 36,878,181
 +
| 4
 +
| 35
 +
| 6
 +
| 0
 +
| 7
 +
|-
 +
| Feeds
 +
| 692 MiB
 +
| 444,014
 +
| 604 MiB
 +
| 5,933,713
 +
| 0
 +
| 8
 +
| 0
 +
| 0
 +
| 3
 +
|-
 +
| MedLineSupp
 +
| 477 MiB
 +
| 1
 +
| 407 MiB
 +
| 21,602,141
 +
| 5
 +
| 55
 +
| 7
 +
| 0
 +
| 9
 +
|-
 +
| AirBase
 +
| 449 MiB
 +
| 38
 +
| 273 MiB
 +
| 14,512,851
 +
| 1
 +
| 111
 +
| 5
 +
| 0
 +
| 11
 +
|-
 +
| MedLineDesc
 +
| 260 MiB
 +
| 1
 +
| 195 MiB
 +
| 10,401,847
 +
| 5
 +
| 66
 +
| 8
 +
| 0
 +
| 9
 +
|-
 +
| ZDNET
 +
| 130 MiB
 +
| 95,663
 +
| 133 MiB
 +
| 3,060,186
 +
| 21
 +
| 40
 +
| 90
 +
| 0
 +
| 13
 +
|-
 +
| JMNEdict
 +
| 124 MiB
 +
| 1
 +
| 171 MiB
 +
| 8,592,666
 +
| 0
 +
| 10
 +
| 0
 +
| 0
 +
| 5
 +
|-
 +
| XMark
 +
| 111 MiB
 +
| 1
 +
| 130 MiB
 +
| 3,221,926
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|-
 +
| Freshmeat
 +
| 105 MiB
 +
| 1
 +
| 86 MiB
 +
| 3,832,028
 +
| 1
 +
| 58
 +
| 1
 +
| 0
 +
| 6
 +
|-
 +
| DeepFS
 +
| 83 MiB
 +
| 1
 +
| 93 MiB
 +
| 4,842,638
 +
| 4
 +
| 3
 +
| 6
 +
| 0
 +
| 21
 +
|-
 +
| Treebank
 +
| 82 MiB
 +
| 1
 +
| 92 MiB
 +
| 3,829,513
 +
| 1
 +
| 250
 +
| 1
 +
| 0
 +
| 37
 +
|-
 +
| DBLP2
 +
| 80 MiB
 +
| 170,843
 +
| 102 MiB
 +
| 4,044,649
 +
| 4
 +
| 35
 +
| 6
 +
| 0
 +
| 6
 +
|-
 +
| DDI
 +
| 76 MiB
 +
| 3
 +
| 39 MiB
 +
| 2,070,157
 +
| 7
 +
| 104
 +
| 16
 +
| 21
 +
| 11
 +
|-
 +
| Alfred
 +
| 75 MiB
 +
| 1
 +
| 68 MiB
 +
| 3,784,285
 +
| 0
 +
| 60
 +
| 0
 +
| 0
 +
| 6
 +
|-
 +
| University
 +
| 56 MiB
 +
| 6
 +
| 66 MiB
 +
| 3,468,606
 +
| 1
 +
| 28
 +
| 4
 +
| 0
 +
| 5
 +
|-
 +
| MediaUKN
 +
| 38 MiB
 +
| 1
 +
| 45 MiB
 +
| 1,619,443
 +
| 3
 +
| 21
 +
| 3
 +
| 0
 +
| 5
 +
|-
 +
| HCIBIB2
 +
| 32 MiB
 +
| 26,390
 +
| 33 MiB
 +
| 617,023
 +
| 1
 +
| 39
 +
| 1
 +
| 0
 +
| 4
 +
|-
 +
| Nasa
 +
| 24 MiB
 +
| 1
 +
| 25 MiB
 +
| 845,805
 +
| 2
 +
| 61
 +
| 8
 +
| 1
 +
| 9
 +
|-
 +
| MovieDB
 +
| 16 MiB
 +
| 1
 +
| 19 MiB
 +
| 868,980
 +
| 6
 +
| 7
 +
| 8
 +
| 0
 +
| 4
 +
|-
 +
| KanjiDic2
 +
| 13 MiB
 +
| 1
 +
| 18 MiB
 +
| 917,833
 +
| 3
 +
| 27
 +
| 10
 +
| 0
 +
| 6
 +
|-
 +
| XMark
 +
| 11 MiB
 +
| 1
 +
| 13 MiB
 +
| 324,274
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|-
 +
| Shakespeare
 +
| 7711 KiB
 +
| 1
 +
| 9854 KiB
 +
| 327,170
 +
| 0
 +
| 59
 +
| 0
 +
| 0
 +
| 9
 +
|-
 +
| TreeOfLife
 +
| 5425 KiB
 +
| 1
 +
| 7106 KiB
 +
| 363,560
 +
| 7
 +
| 4
 +
| 7
 +
| 0
 +
| 243
 +
|-
 +
| Thesaurus
 +
| 4288 KiB
 +
| 1
 +
| 4088 KiB
 +
| 201,798
 +
| 7
 +
| 33
 +
| 9
 +
| 0
 +
| 7
 +
|-
 +
| MusicXML
 +
| 3155 KiB
 +
| 17
 +
| 2942 KiB
 +
| 171,400
 +
| 8
 +
| 179
 +
| 56
 +
| 0
 +
| 8
 +
|-
 +
| BibDBPub
 +
| 2292 KiB
 +
| 3,465
 +
| 2359 KiB
 +
| 80,178
 +
| 1
 +
| 54
 +
| 1
 +
| 0
 +
| 4
 +
|-
 +
| Factbook
 +
| 1743 KiB
 +
| 1
 +
| 1560 KiB
 +
| 77,315
 +
| 16
 +
| 23
 +
| 32
 +
| 0
 +
| 6
 +
|-
 +
| XMark
 +
| 1134 KiB
 +
| 1
 +
| 1334 KiB
 +
| 33,056
 +
| 2
 +
| 74
 +
| 9
 +
| 0
 +
| 13
 +
|}
  
 
== Sources ==
 
== Sources ==

Revision as of 14:22, 16 February 2011

The following table lists statistics on various XML instances that have been created with BaseX and, if available or public, links to the source documents.

The database size does not include any indexes

  • #nodes represents the number of XML nodes which have been created in the database
  • #atr, #eln, and #uri represent the number of distinct attributes, element names, and namespaces

Databases

Instances file size #files db size #db nodes #atr #eln #atn #uri height
RuWikiHist 421 GiB 1 416 GiB 324,848,508 3 21 6 2 6
ZhWikiHist 126 GiB 1 120 GiB 179,199,662 3 21 6 2 6
EnWiktionary 79 GiB 1 75 GiB 134,380,393 3 21 6 2 6
XMark 55 GiB 1 64 GiB 1,615,071,348 2 74 9 0 13
EnWikiMeta 54 GiB 1 52 GiB 401,456,348 3 21 6 2 6
MedLine 38 GiB 379 36 GiB 1,623,764,254 2 84 6 0 9
iProClass 36 GiB 1 37 GiB 1,631,218,984 3 245 4 2 9
Inex209 31 GiB 2,666,500 34 GiB 1,336,110,639 15 28,034 451 1 37
CoPhIR 29 GiB 10,000,000 31 GiB 1,104,623,376 10 42 42 0 8
EnWikipedia 26 GiB 1 25 GiB 198,546,747 3 24 21 2 6
XMark 22 GiB 1 26 GiB 645,997,965 2 74 9 0 13
InterPro 14 GiB 1 19 GiB 860,304,235 5 7 15 0 4
Genome1 13 GiB 1 13 GiB 432,628,105 12 26 101 2 6
NewYorkTimes 12 GiB 1,855,659 13 GiB 280,407,005 5 41 33 0 6
TrEMBL 11 GiB 1 14 GiB 589,650,535 8 47 30 2 7
XMark 11 GiB 1 13 GiB 323,083,409 2 74 9 0 13
IntAct 7973 MiB 25,624 6717 MiB 297,478,392 7 64 22 2 14
Freebase 7366 MiB 1 10 GiB 443,627,994 8 61 283 1 93
SDMX 6356 MiB 1 8028 MiB 395,871,872 2 22 6 3 7
OpenStreetMap 5312 MiB 1 5171 MiB 6,910,669 3 19 5 2 6
SwissProt 4604 MiB 1 5422 MiB 241,274,406 8 70 39 2 7
EURLex 4815 MiB 1 5532 MiB 167,328,039 23 186 46 1 12
Wikicorpus 4492 MiB 659,338 4432 MiB 157,948,561 12 1,257 2,687 2 50
EnWikiRDF 3679 MiB 1 3537 MiB 98,433,194 1 11 2 11 4
CoPhIR 2695 MiB 1,000,000 2882 MiB 101,638,857 10 42 42 0 8
MeSH 2091 MiB 1 2410 MiB 104,845,819 3 6 5 2 5
FreeDB 1723 MiB 1 2462 MiB 102,901,519 2 7 3 0 4
XMark 1134 MiB 1 1303 MiB 32,298,989 2 74 9 0 13
DeepFS 810 MiB 1 850 MiB 44,821,506 4 3 6 0 24
LibraryUKN 760 MiB 1 918 MiB 46,401,941 3 23 3 0 5
Twitter 736 MiB 1,177,495 767 MiB 15,309,015 0 8 0 0 3
Organizations 733 MiB 1,019,132 724 MiB 33,112,392 3 38 9 0 7
DBLP 694 MiB 1 944 MiB 36,878,181 4 35 6 0 7
Feeds 692 MiB 444,014 604 MiB 5,933,713 0 8 0 0 3
MedLineSupp 477 MiB 1 407 MiB 21,602,141 5 55 7 0 9
AirBase 449 MiB 38 273 MiB 14,512,851 1 111 5 0 11
MedLineDesc 260 MiB 1 195 MiB 10,401,847 5 66 8 0 9
ZDNET 130 MiB 95,663 133 MiB 3,060,186 21 40 90 0 13
JMNEdict 124 MiB 1 171 MiB 8,592,666 0 10 0 0 5
XMark 111 MiB 1 130 MiB 3,221,926 2 74 9 0 13
Freshmeat 105 MiB 1 86 MiB 3,832,028 1 58 1 0 6
DeepFS 83 MiB 1 93 MiB 4,842,638 4 3 6 0 21
Treebank 82 MiB 1 92 MiB 3,829,513 1 250 1 0 37
DBLP2 80 MiB 170,843 102 MiB 4,044,649 4 35 6 0 6
DDI 76 MiB 3 39 MiB 2,070,157 7 104 16 21 11
Alfred 75 MiB 1 68 MiB 3,784,285 0 60 0 0 6
University 56 MiB 6 66 MiB 3,468,606 1 28 4 0 5
MediaUKN 38 MiB 1 45 MiB 1,619,443 3 21 3 0 5
HCIBIB2 32 MiB 26,390 33 MiB 617,023 1 39 1 0 4
Nasa 24 MiB 1 25 MiB 845,805 2 61 8 1 9
MovieDB 16 MiB 1 19 MiB 868,980 6 7 8 0 4
KanjiDic2 13 MiB 1 18 MiB 917,833 3 27 10 0 6
XMark 11 MiB 1 13 MiB 324,274 2 74 9 0 13
Shakespeare 7711 KiB 1 9854 KiB 327,170 0 59 0 0 9
TreeOfLife 5425 KiB 1 7106 KiB 363,560 7 4 7 0 243
Thesaurus 4288 KiB 1 4088 KiB 201,798 7 33 9 0 7
MusicXML 3155 KiB 17 2942 KiB 171,400 8 179 56 0 8
BibDBPub 2292 KiB 3,465 2359 KiB 80,178 1 54 1 0 4
Factbook 1743 KiB 1 1560 KiB 77,315 16 23 32 0 6
XMark 1134 KiB 1 1334 KiB 33,056 2 74 9 0 13

Sources

InstancesSource
AirBasehttp://air-climate.eionet.europa.eu/databases/airbase/airbasexml
Alfredhttp://alfred.med.yale.edu/alfred/alfredWithDescription.zip
BibDBPubhttp://inex.is.informatik.uni-duisburg.de/2005/
CoPhIRhttp://cophir.isti.cnr.it/
DBLPhttp://dblp.uni-trier.de/xml
DBLP2http://inex.is.informatik.uni-duisburg.de/2005/
DDIhttp://tools.ddialliance.org/
EnWikiMetahttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-meta-current.xml.bz2
EnWikipediahttp://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2
EnWikiRDFhttp://www.xml-benchmark.org/  generated with xmlgen
EnWiktionaryhttp://dumps.wikimedia.org/enwiktionary/latest/enwiktionary-latest-pages-meta-history.xml.7z
EURLexhttp://www.epsiplatform.eu/
Factbookhttp://www.cs.washington.edu/research/xmldatasets/www/repository.html
Freebasehttp://download.freebase.com/wex
FreeDBhttp://www.xmldatabases.org/radio/xmlDatabases/projects/FreeDBtoXML
Freshmeathttp://freshmeat.net/articles/freshmeat-xml-rpc-api-available
Genome1ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606/XML/ds_ch1.xml.gz
HCIBIB2http://inex.is.informatik.uni-duisburg.de/2005/
Inex2009http://www.mpi-inf.mpg.de/departments/d5/software/inex
IntActftp://ftp.ebi.ac.uk/pub/databases/intact/current/index.html
InterProftp://ftp.bio.net/biomirror/interpro/match_complete.xml.gz
iProClassftp://ftp.pir.georgetown.edu/pir_databases/iproclass/iproclass.xml.gz
JMNEdictftp://ftp.monash.edu.au/pub/nihongo/enamdict_doc.html
KanjiDic2http://www.csse.monash.edu.au/~jwb/kanjidic2
MedLinehttp://www.nlm.nih.gov/bsd
MeSHhttp://www.nlm.nih.gov/mesh/xmlmesh.html
MovieDBhttp://eagereyes.org/InfoVisContest2007Data.html
MusicXMLhttp://www.recordare.com/xml/samples.html
Nasahttp://www.cs.washington.edu/research/xmldatasets/www/repository.html
NewYorkTimeshttp://www.nytimes.com/ref/membercenter/nytarchive.html
OpenStreetMaphttp://dump.wiki.openstreetmap.org/osmwiki-latest-files.tar.gz
Organizationshttp://www.data.gov/raw/1358
RuWikiHisthttp://dumps.wikimedia.org/ruwiki/latest/ruwiki-latest-pages-meta-history.xml.7z
SDMXhttp://www.metadatatechnology.com/
Shakespearehttp://www.cafeconleche.org/examples/shakespeare
SwissProtftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase
Thesaurushttp://www.drze.de/BELIT/thesaurus
Treebankhttp://www.cs.washington.edu/research/xmldatasets
TreeOfLifehttp://tolweb.org/data/tolskeletaldump.xml
TrEMBLftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase
Wikicorpushttp://www-connex.lip6.fr/~denoyer/wikipediaXML
XMarkhttp://www.xml-benchmark.org/  generated with xmlgen
ZDNEThttp://inex.is.informatik.uni-duisburg.de/2005/
ZhWikiHisthttp://dumps.wikimedia.org/zhwiki/latest/zhwiki-latest-pages-meta-history.xml.7z
LibraryUKNgenerated from university library data
MediaUKNgenerated from university library data
DeepFSgenerated from filesystem structure
Universitygenerated from students test data
Feedscompiled from news feeds
Twittercompiled from Twitter feeds